This paper proposes the use of neural networks as a tool for studying navigation within virtual worlds. Results indicate that the network learned to predict the next step for a given trajectory. The analysis of hidden layer shows that the network was able to differentiate between two groups of users identified on the basis of their performance for a spatial task. Time series analysis of hidden node activation values and input vectors suggested that certain hidden units become specialised for place and heading, respectively. The benefits of this approach and the possibility of extending the methodology to the study of navigation in Human Computer Interaction applications are discussed.