INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    toolStrip
    -0.84
      [
    -0.83
    Alec
    -0.81
     hikay
    -0.81
     fühlen
    -0.79
    Nodo
    -0.78
    IDEO
    -0.78
    -0.78
     inşa
    -0.77
     biograf
    -0.77
    POSITIVE LOGITS
    imageView
    1.27
     image
    1.14
     button
    1.11
    Button
    1.11
    ImageView
    1.06
     imageView
    1.05
    button
    1.05
     Button
    1.02
     ImageView
    1.01
     img
    0.95
    Act Density 0.015%

    No Known Activations