INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    kins
    -0.89
    KINS
    -0.68
    bootstrapcdn
    -0.61
    Personendaten
    -0.60
    AutoScale
    -0.60
    Dropout
    -0.57
    ")));
    
    -0.54
    ftagPool
    -0.54
    ?')
    -0.53
    yarnpkg
    -0.53
    POSITIVE LOGITS
     MainAxisSize
    0.50
    arakhand
    0.49
     Paprika
    0.49
     تضيفلها
    0.48
    expandindo
    0.48
    іга
    0.46
    rechter
    0.44
     painted
    0.44
     PeEnEo
    0.43
     Cabbage
    0.43
    Act Density 0.035%

    No Known Activations