INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ness
    -0.52
    шні
    -0.49
    ny
    -0.48
    -0.47
    l
    -0.44
    nya
    -0.43
    stu
    -0.42
    ry
    -0.42
     Dal
    -0.41
    rate
    -0.41
    POSITIVE LOGITS
    parsedMessage
    0.93
     disambiguazione
    0.75
    InputBorder
    0.71
    titleMargin
    0.66
    contentLoaded
    0.65
     متعلقه
    0.65
     مرئيه
    0.60
    AndEndTag
    0.58
    PageContext
    0.57
    UserScript
    0.57
    Act Density 0.001%

    No Known Activations