INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    IndentedString
    -0.56
     MainAxisSize
    -0.43
     estekak
    -0.42
    )"),
    -0.42
     beginnetje
    -0.42
    djangoproject
    -0.41
    '))
    
    -0.40
    ifflin
    -0.39
     ویکی‌آمباردا
    -0.39
    ')).
    -0.39
    POSITIVE LOGITS
     class
    0.84
    class
    0.68
     Class
    0.63
     classe
    0.61
     CLASS
    0.60
    Class
    0.59
     clase
    0.54
     kelas
    0.53
     Klasse
    0.52
     cérami
    0.52
    Act Density 0.008%

    No Known Activations