INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    UnknownFields
    -0.62
    клопе
    -0.47
    manjaro
    -0.46
    ResumeLayout
    -0.45
    ReusableCell
    -0.44
     folds
    -0.39
    ipi
    -0.39
    ennials
    -0.39
    ticello
    -0.39
    ractable
    -0.38
    POSITIVE LOGITS
     Савезне
    0.82
     يتيمه
    0.68
    hoeddwyd
    0.68
    حياتها
    0.65
    AddTagHelper
    0.63
     poveznice
    0.63
     للمعارف
    0.61
    IUrlHelper
    0.61
    حياته
    0.60
     دیکھیے
    0.58
    Act Density 0.055%

    No Known Activations