INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    struct
    0.84
     class
    0.82
    class
    0.78
    0.78
     Interface
    0.77
    interface
    0.76
     interfaces
    0.76
    component
    0.73
     interface
    0.73
     класса
    0.73
    POSITIVE LOGITS
     signature
    1.12
     Signature
    1.09
    Signature
    0.99
    signature
    0.93
     signatures
    0.88
     sig
    0.77
    signatures
    0.76
    签名
    0.71
     रिसी
    0.68
     परिभाषा
    0.67
    Act Density 0.280%

    No Known Activations