Chemical exposure can cause formative neurotoxicity, which requires fast and exact testing techniques. Current methods, notably in vivo research on animal models and assessments of primary cell cultures derived from animal and humans, have difficulties in terms of time, expense, and application to human physiology. For example, in vivo animal studies may take years to complete. In this study, eXplainable Artificial Intelligence (XAI) was combined with XGBoost machine learning (ML) models that were prepared to utilize binary classification as a potent mix of datasets to identify genes that may be associated with neurotoxicity. Significant genes were found and connected to the progression of neurotoxicity after SHAP values were effectively integrated into the ML models.