INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     만나
    -0.06
     ấm
    -0.06
     objs
    -0.06
    .astype
    -0.06
    -0.06
    -src
    -0.06
     thankful
    -0.06
    bitmap
    -0.06
    	      
    -0.06
    ↵    
    ↵
    -0.06
    POSITIVE LOGITS
     تواند
    0.08
    |=
    0.07
    >,</
    0.07
    oli
    0.07
    ات
    0.06
    meric
    0.06
    ‌تواند
    0.06
    DidLoad
    0.06
    FORCE
    0.06
    ividad
    0.06
    Act Density 0.002%

    No Known Activations