INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     kug
    -0.08
     Korn
    -0.07
     دائ
    -0.07
     supervised
    -0.07
     França
    -0.07
     jurisdiction
    -0.07
     FK
    -0.07
     people
    -0.07
     وخت
    -0.07
    _gpu
    -0.07
    POSITIVE LOGITS
     ним
    0.10
    _Control
    0.09
    _LOGIN
    0.09
    бав
    0.09
    _Add
    0.09
    _All
    0.08
    _Login
    0.08
     geïnteresseerd
    0.08
    0.08
    _Selected
    0.08
    Act Density 0.005%

    No Known Activations