INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Blake
    -1.73
    Blake
    -1.48
    ize
    -0.48
    Erstellt
    -0.48
    scra
    -0.46
    setOpaque
    -0.45
    shu
    -0.44
    importanza
    -0.44
    chiede
    -0.44
    sein
    -0.44
    POSITIVE LOGITS
     مرئيه
    0.82
    ItemBackground
    0.79
    InputBorder
    0.70
    tagHelperRunner
    0.69
    ArrowToggle
    0.68
    sizeCache
    0.68
    djangoproject
    0.68
     '\\;'
    0.68
     "..\..\..\
    0.67
     переписи
    0.67
    Act Density 1.873%

    No Known Activations