I am trying to implement Isolation forest for anomaly detection but I am not able to understand and visualise the decision function

I am trying to implement Isolation forest for anomaly detection but I am not able to understand the scores. Also, I want to plot and visualise the decision function that my Isolation forest is creating.

Below is the code that I have written :

def IForest(df):
    clf = IsolationForest(n_estimators = 300, contamination = 0.01, behaviour = "new")
    clf.fit(df)
    anomaly_score = clf.decision_function(df)
    anomalies = clf.predict(df)
    print("n Decision function for Isolation forest")
    print(anomaly_score)
    print("n The label -1 suggests that the point is anomolous and 1 suggests that the point is normal")
    print(anomalies)
    anomolus_dp = data[np.where(outlier == -1, True, False)]
    print("nThe data has {} anomolus points and the data points are the following for  : ".format(len(anomolus_dp)))
    print(anomolus_dp)

The output that I am getting is the following :

On what basis is this score -0.01010126 is classified ? It is not the probablity of a data point to be considered an anomaly and why is -1(suggesting anomaly) assigned to it, then how can I get the probablity of a a data point to be considered anomlous ?
Also, How do I understand which variable(s) is contributing for this data point to be classified as anomaly ?