INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    sum
    -0.53
    oxi
    -0.47
     Sum
    -0.47
    Bretagne
    -0.46
    سكري
    -0.44
    mailto
    -0.44
    setName
    -0.44
    -0.44
     Finally
    -0.44
     Orlando
    -0.44
    POSITIVE LOGITS
     '\\;'
    0.88
    adaptiveStyles
    0.77
    клопе
    0.71
     NSCoder
    0.68
    ніципалі
    0.64
    resizingMask
    0.64
    twimg
    0.61
    rebbero
    0.61
     pinulongan
    0.60
     CommonModule
    0.60
    Act Density 0.097%

    No Known Activations