INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    _METHOD
    -0.07
    	border
    -0.07
    .digital
    -0.06
    XX
    -0.06
     пар
    -0.06
    uebas
    -0.06
    google
    -0.06
    tesy
    -0.06
     جهان
    -0.06
    ems
    -0.06
    POSITIVE LOGITS
     rost
    0.07
     Leicester
    0.06
     goalkeeper
    0.06
     neurological
    0.06
     completing
    0.06
    touches
    0.06
     Advent
    0.06
    term
    0.06
     رئیس
    0.06
    {(
    0.06
    Act Density 0.032%

    No Known Activations