INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     mezun
    -0.07
    (Convert
    -0.06
     گوشی
    -0.06
    535
    -0.06
    getStyle
    -0.06
    _minute
    -0.06
    Panel
    -0.06
    .Adapter
    -0.06
     publishes
    -0.06
    .control
    -0.05
    POSITIVE LOGITS
    -hidden
    0.17
    @example
    0.15
     Brewery
    0.13
     brewery
    0.13
     breweries
    0.11
     frameborder
    0.07
     Wal
    0.07
    Gam
    0.07
    tolua
    0.07
    ξη
    0.07
    Act Density 0.003%

    No Known Activations