Hey Lian, the confusion matrix shows you different things like TP, FP, FN, TN in one diagram. For example, the diagonal line represents the TP (True Positives) and the row of a class represents FN (Fales Negatives).

In this confusion matrix I decided to represent the numbers in percentage instead of absolut numbers. Both ways are correct.

If you want to look for precision, recall, accuracy and F1 of each class. I highly recommend to you the classification_report function of scikit-learn.

https://scikit-learn.org/stable/modules/generated/sklearn.metrics.classification_report.html#sklearn.metrics.classification_report

In addition check out that wonderful articel about multi-class confusion matrix: https://saxsau.medium.com/introduction-to-confusion-matrix-31168782711a

I hope that helps you?