INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     information
    -0.06
     nag
    -0.06
    xiety
    -0.06
    важ
    -0.06
    354
    -0.06
     coisa
    -0.06
    =log
    -0.06
     boyunca
    -0.06
     fullName
    -0.06
    
    -0.06
    POSITIVE LOGITS
     opens
    0.07
     offensive
    0.07
     appar
    0.07
     Offensive
    0.06
    Expanded
    0.06
    UIImageView
    0.06
    xmin
    0.06
    Pixel
    0.06
    (Audio
    0.06
     friendly
    0.06
    Act Density 0.003%

    No Known Activations