INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    expandindo
    -0.97
    ########.
    -0.90
    Their
    -0.68
     betweenstory
    -0.65
     referenties
    -0.65
     Itself
    -0.61
     themselves
    -0.60
     Their
    -0.60
    ArrowToggle
    -0.59
    themselves
    -0.58
    POSITIVE LOGITS
     the
    0.91
    CPtr
    0.65
    MemoryWarning
    0.58
     محفوظة
    0.57
     ویکی‌پدیا
    0.54
    heit
    0.51
    indrome
    0.48
    bootstrapcdn
    0.48
    ChildScrollView
    0.47
    (!__
    0.47
    Act Density 0.119%

    No Known Activations