This paper proposes the use of neural networks as a tool for studying navigation within virtual worlds. Results indicate that network learned to predict the next step for a given trajectory, acquiring also basic spatial knowledge in terms of landmarks and configuration of spatial layout. In addition, the network built a spatial representation of the virtual world, e.g. cognitive-like map, which preserves the topology but lacks metric accuracy. The benefits of this approach and the possibility of extending the methodology to the study of navigation in Human Computer Interaction are discussed.