INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    iest
    -0.44
     surla
    -0.42
     InputDecoration
    -0.40
    cipal
    -0.39
     ivelany
    -0.37
    eqn
    -0.37
     pater
    -0.36
    tiest
    -0.36
     quai
    -0.35
     Israeli
    -0.35
    POSITIVE LOGITS
     colgantes
    0.55
    antaranya
    0.54
    contentLoaded
    0.53
     Winaray
    0.50
     caminhada
    0.49
    hamilan
    0.48
    endphp
    0.48
     satunya
    0.48
     mahdol
    0.47
    endpush
    0.47
    Act Density 0.032%

    No Known Activations