INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     McG
    -0.07
     ag
    -0.06
    eea
    -0.06
     Reed
    -0.06
    (com
    -0.06
     deaths
    -0.06
     Packs
    -0.06
     USERS
    -0.06
     iterations
    -0.06
    lb
    -0.06
    POSITIVE LOGITS
    ameron
    0.08
    HW
    0.08
     Horizontal
    0.07
     QHBoxLayout
    0.07
    					    
    0.07
     horizontal
    0.07
    Textbox
    0.07
    horizontal
    0.07
    ourt
    0.07
     yapıyor
    0.07
    Act Density 0.004%

    No Known Activations