INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     erót
    -0.07
       
    -0.07
    _CYCLE
    -0.07
     robes
    -0.07
     uncertainty
    -0.07
    	
    -0.07
    .btnCancel
    -0.07
     CST
    -0.06
    _OPEN
    -0.06
     harder
    -0.06
    POSITIVE LOGITS
    0.07
     Battery
    0.07
    ʃ
    0.07
     נהנ
    0.07
    0.07
    IndexOf
    0.07
    eteria
    0.07
    0.06
    reshape
    0.06
    PostBack
    0.06
    Act Density 0.066%

    No Known Activations