Boolean networks offer a powerful framework for modeling gene interactions, providing valuable insights into cellular behavior and disease mechanisms. Identifying key genes is critical for advancing scientific understanding and drug development, but the complexity of biological networks often requires extensive simulations that are difficult to interpret. This paper investigates a novel approach for evaluating gene importance within Boolean networks, using Shapley values from cooperative game theory. The method quantifies each gene’s contribution to overall network behavior, yielding a metric for gene importance. We demonstrate the method’s effectiveness using a case study on the CD4+ T cell differentiation model, validating our predictions against established literature. Additionally, we compare this approach with traditional network analysis metrics to highlight its advantages. We further evaluate the method’s scalability across six models of different sizes, concluding that it is particularly well-suited for small to medium-scale networks. Lastly, we explore potential improvements through the application of network propagation techniques.