We have studied the distribution of traffic flow q for the Nagel-Schreckenberg model by computer simulations. We applied a large-deviation approach, which allowed us to obtain the distribution P (q) over more than one hundred decades in probability, down to probabilities like 10 −140 . This allowed us to characterize the flow distribution over a large range of the support and identify the characteristics of rare and even very rare traffic situations. We observe a change of the distribution shape when increasing the density of cars from the free flow to the congestion phase. Furthermore, we characterize typical and rare traffic situations by measuring correlations of q to other quantities like density of standing cars or number and size of traffic jams.