INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     پرد
    -0.08
     صرف
    -0.07
     sede
    -0.06
    <meta
    -0.06
    VICES
    -0.06
     crawler
    -0.06
     Curse
    -0.06
     helpless
    -0.06
     کاری
    -0.06
    <Role
    -0.06
    POSITIVE LOGITS
     homers
    0.07
     admired
    0.06
     edi
    0.06
    0.06
    teil
    0.06
     nuôi
    0.06
     číslo
    0.06
     subtitle
    0.06
     clr
    0.06
    ται
    0.06
    Act Density 0.048%

    No Known Activations