INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     metal
    -0.06
    mes
    -0.06
    ажд
    -0.06
    _global
    -0.06
     pierced
    -0.06
    _ACTIVITY
    -0.06
     invert
    -0.06
    .slot
    -0.06
    	control
    -0.06
     اصلی
    -0.06
    POSITIVE LOGITS
     cx
    0.08
     Lebanese
    0.07
     підт
    0.07
    licken
    0.07
    offee
    0.07
    //
    ↵
    0.06
     bam
    0.06
    devil
    0.06
    athlete
    0.06
    renal
    0.06
    Act Density 0.015%

    No Known Activations