INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     thor
    -0.06
     دقیقه
    -0.06
    idge
    -0.06
     Aero
    -0.06
     joy
    -0.06
    -0.06
     мар
    -0.06
     getPage
    -0.06
     rainfall
    -0.06
    _cards
    -0.05
    POSITIVE LOGITS
     abnormalities
    0.10
    matched
    0.07
    Tar
    0.07
    mtx
    0.07
     Ih
    0.06
    0.06
    П
    0.06
     backgrounds
    0.06
    *******
    0.06
    ALE
    0.06
    Act Density 0.013%

    No Known Activations