Text Multiclass classifcation - model explainability question

Hello!
I have successfully trained model based on example: [GitHub Issue Classification](https://github.com/dotnet/machinelearning-samples/tree/main/samples/csharp/end-to-end-apps/MulticlassClassification-GitHubLabeler
)
I have modified program to train a model using only one of the features from the data.
The model is behaving accurately, but I would like to know why. Is there a way, to calculate what word/combination of words caused specific prediction in text classification problem?