INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    kou
    -0.07
    NewLabel
    -0.07
    	wait
    -0.06
     cyl
    -0.06
     sleek
    -0.06
     theirs
    -0.06
     dialogRef
    -0.06
     кле
    -0.06
    ViewController
    -0.06
     KB
    -0.06
    POSITIVE LOGITS
    .TypeOf
    0.07
     جر
    0.07
     nomin
    0.07
     garden
    0.07
     kitchen
    0.07
     finans
    0.07
     luxury
    0.07
     اقتصاد
    0.07
    ับสน
    0.06
    0.06
    Act Density 0.001%

    No Known Activations