Viable modifications of gravity that may produce cosmic acceleration need to be screened in high-density regions such as the Solar System, where general relativity is well tested. Screening mechanisms also prevent strong anomalies in the large-scale structure and limit the constraints that can be inferred on these gravity models from cosmology. We find that by suppressing the contribution of the screened high-density regions in the matter power spectrum, allowing a greater contribution of unscreened low densities, modified gravity models can be more readily discriminated from the concordance cosmology. Moreover, by variation of density thresholds, degeneracies with other effects may be dealt with more adequately. Specializing to chameleon gravity as a worked example for screening in modified gravity, employing N -body simulations of f (R) models and the halo model of chameleon theories, we demonstrate the effectiveness of this method. We find that a percent-level measurement of the clipped power at k < 0.3 h/Mpc can yield constraints on chameleon models that are more stringent than what is inferred from Solar System tests or distance indicators in unscreened dwarf galaxies. Finally, we verify that our method is also applicable to the Vainshtein mechanism.Introduction.-Determining the nature of the accelerated expansion of our Universe is a prime endeavor to cosmologists. In the conventional picture, the flat Λ cold dark matter (ΛCDM) concordance model based on general relativity (GR), a cosmological constant Λ contributes the bulk of the present energy density in the cosmos and drives the late-time acceleration. While alternatively, a modification of gravity may be responsible for cosmic acceleration, stringent limitations from experiments within our Solar System must be satisfied. A number of screening mechanisms [1-5] have been identified that can suppress modifications of gravity in high-density regions to recover GR, while still generating significant modifications within lower densities on larger, cosmological scales. However, this suppression effect, along with other nonlinear effects, also prevents strong anomalies from manifesting in the averaged large-scale structure of our Universe [6] and limits the constraints that can be inferred on these gravity models from cosmology.Given the density dependence of the screening effect, in this Letter, we propose the downweighting of highdensity regions in statistical observables such as the matter power spectrum P (k) to enhance, or unscreen, the signatures of modified gravity and improve observational constraints. Such a weighting is conducted in the clipping method of Ref. [7], with the original motivation of facilitating the modeling of P (k) by reducing contributions of high densities, where the assumptions of perturbation theory break down. As a worked example, we first focus on Hu-Sawicki [8] f (R) gravity [9], which employs the chameleon screening mechanism [2]. We analyze effects on the power spectrum from clipping density fields in numerical simulations ...