INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     R
    -0.57
     B
    -0.49
     M
    -0.48
    R
    -0.47
    B
    -0.45
     N
    -0.43
     E
    -0.42
     W
    -0.42
    jat
    -0.41
     pre
    -0.41
    POSITIVE LOGITS
    DoubleQuotes
    1.05
     MenuView
    1.02
    تقاوى
    0.98
     мәкал
    0.96
    BufferException
    0.95
     мәкалә
    0.94
    PerformLayout
    0.94
     يتيمه
    0.93
    TintMode
    0.90
    tagHelperRunner
    0.89
    Act Density 1.334%

    No Known Activations