INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    wiąz
    -0.07
     interpreter
    -0.07
    $link
    -0.07
     Turkish
    -0.07
    ху
    -0.06
     actors
    -0.06
     restaur
    -0.06
    iy
    -0.06
    _cats
    -0.06
    ัน
    -0.06
    POSITIVE LOGITS
    ,所以
    0.07
    .inv
    0.06
     гір
    0.06
    	for
    0.06
     tableLayoutPanel
    0.06
    ¯¯
    0.06
    0.06
    سين
    0.06
     contributed
    0.06
     сохра
    0.06
    Act Density 0.024%

    No Known Activations