INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    @section
    -0.07
    -decoration
    -0.07
    _average
    -0.07
    graphics
    -0.07
     Passport
    -0.07
    ообраз
    -0.06
     CLOSED
    -0.06
     Tattoo
    -0.06
    specialchars
    -0.06
    .definition
    -0.06
    POSITIVE LOGITS
    0.07
     Birleşik
    0.07
    -client
    0.07
    0.06
    0.06
    sgi
    0.06
     stratej
    0.06
     کار
    0.06
     asi
    0.06
    Dem
    0.06
    Act Density 0.000%

    No Known Activations