INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     pareja
    -0.07
     Pero
    -0.06
     قلب
    -0.06
    -0.06
    ulo
    -0.06
    Pedido
    -0.06
    	tile
    -0.06
    velopment
    -0.06
    	des
    -0.06
     Pie
    -0.06
    POSITIVE LOGITS
    _lbl
    0.07
     downtime
    0.06
     superClass
    0.06
     Almost
    0.06
    Index
    0.06
     Motorola
    0.06
     Alban
    0.06
     binder
    0.06
    amount
    0.06
     Got
    0.06
    Act Density 0.015%

    No Known Activations