INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    FormTagHelper
    -0.62
    Попис
    -0.57
    RenderAtEndOf
    -0.51
    atility
    -0.51
     AppCompatTheme
    -0.49
     المعيارى
    -0.49
    mique
    -0.48
    ۜ
    -0.48
     interstate
    -0.48
     HttpNotFound
    -0.47
    POSITIVE LOGITS
    Obrázky
    0.67
     plastiques
    0.59
     supérieurs
    0.57
     supérieures
    0.56
    Pair
    0.54
     financières
    0.54
    pair
    0.53
     Pair
    0.52
     juridiques
    0.52
     suivants
    0.51
    Act Density 0.021%

    No Known Activations