INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     namn
    -0.46
     đi
    -0.46
    -0.45
    rus
    -0.45
     hand
    -0.44
     فريبيس
    -0.43
     caught
    -0.43
    vgili
    -0.43
    trina
    -0.43
    titia
    -0.43
    POSITIVE LOGITS
    تقاوى
    0.96
     مشين
    0.85
     BorderRadius
    0.84
    GraphicsUnit
    0.82
    \{\\
    0.78
     TextInputType
    0.78
     Touchable
    0.76
     AssemblyCulture
    0.73
     snippetHide
    0.72
     protoimpl
    0.70
    Act Density 0.089%

    No Known Activations