INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     हिंदी
    -0.08
    -0.08
     voc
    -0.08
     Vocal
    -0.08
     composed
    -0.07
    -0.07
    -0.07
    itsonga
    -0.07
    HOR
    -0.07
     автобус
    -0.07
    POSITIVE LOGITS
     solvent
    0.08
     cork
    0.07
    در
    0.07
     Cork
    0.07
     Streit
    0.07
     Supplemental
    0.07
    /el
    0.07
    ف
    0.07
    deur
    0.07
     Stim
    0.07
    Act Density 0.001%

    No Known Activations