INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    MC
    -0.06
     MATCH
    -0.06
     захід
    -0.06
     centre
    -0.06
    Soup
    -0.06
     FontStyle
    -0.06
     LIN
    -0.06
     gridColumn
    -0.06
    epoch
    -0.06
    _orient
    -0.06
    POSITIVE LOGITS
    0.06
    rought
    0.06
    arios
    0.06
    0.06
    /frontend
    0.06
    0.05
     unveiled
    0.05
     číslo
    0.05
     Made
    0.05
    aje
    0.05
    Act Density 0.025%

    No Known Activations