INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.43
     تعدى
    -0.41
    Care
    -0.40
    TR
    -0.39
    Filmografie
    -0.38
     duy
    -0.37
    very
    -0.36
     CON
    -0.35
     occident
    -0.35
     acompan
    -0.34
    POSITIVE LOGITS
    الحياه
    0.82
    +:+
    0.77
     للاسماء
    0.74
    UseVisualStyle
    0.73
     ✭✭
    0.72
    LookAnd
    0.71
    principalColumn
    0.71
     JpaRepository
    0.69
    __':
    
    0.69
    enderror
    0.68
    Act Density 0.010%

    No Known Activations