Evolutionary Robotics is a research field focused on autonomous design of robots based on evolutionary algorithms. In this field, neuroevolution methods aims in particular at designing both structure and parameters of neural networks that make a robot exhibit a desired behavior. While such methods have shown their efficiency to generate reactive behaviors, they hardly scale to more cognitive behaviors. One of the reasons of such a limitation might be in the properties of the encoding, i.e. the neural network representation explored by the genetic operators. This work considers EvoNeuro encoding, an encoding directly inspired from computational neuroscience and tests its efficiency on a working memory task, namely the AX-CPT task. Neural networks able to solve this task are generated and compared to neural networks evolved with a simpler direct encoding. The task is solved in both cases, but while direct encodings tend to generate networks whose structure is adapted to a particular instance of AX-CPT, networks generated with EvoNeuro encoding are more versatile and can adapt to the new task through a simple parameter optimization. Such versatile neural networks might facilitate the evolution of robot controllers for tasks requiring a working memory.