INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     kok
    0.46
     fra
    0.46
     dank
    0.44
     Dank
    0.42
    ילות
    0.42
    aga
    0.42
    اکي
    0.42
    ită
    0.41
     gazed
    0.40
     untapped
    0.40
    POSITIVE LOGITS
     Clipboard
    0.44
     Polynomial
    0.41
    貸款
    0.40
     С
    0.38
    ForeColor
    0.38
    enamefont
    0.38
    Curr
    0.38
     பஞ்ச
    0.38
    الإنجليزية
    0.38
    0.37
    Act Density 0.001%

    No Known Activations