INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Geb
    -0.07
     hyper
    -0.07
    _warn
    -0.07
     Bas
    -0.07
     Foo
    -0.07
    apan
    -0.07
     Zaman
    -0.07
     Cedar
    -0.06
    zan
    -0.06
     composed
    -0.06
    POSITIVE LOGITS
     onc
    0.08
     Onc
    0.08
    .SizeType
    0.07
    _UNKNOWN
    0.07
     loại
    0.06
     شهری
    0.06
    larındaki
    0.06
    ioneer
    0.06
    ्ञ
    0.06
     Inn
    0.06
    Act Density 0.003%

    No Known Activations