INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     vostri
    -0.62
     boxeo
    -0.59
    expandindo
    -0.57
    collect
    -0.57
     IFT
    -0.56
     vosotros
    -0.54
    rds
    -0.54
     IZ
    -0.53
     fér
    -0.52
    яза
    -0.52
    POSITIVE LOGITS
    i
    1.84
    iK
    0.97
    iM
    0.77
    0.75
    ipo
    0.74
     BoxDecoration
    0.70
    iation
    0.69
    iin
    0.68
    iT
    0.67
    iP
    0.67
    Act Density 0.192%

    No Known Activations