INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     nadr
    -0.08
     sıra
    -0.08
    ıc
    -0.08
    اليب
    -0.07
    (enabled
    -0.07
    PU
    -0.07
    -0.07
     Trab
    -0.07
    	fields
    -0.07
     SX
    -0.07
    POSITIVE LOGITS
     нос
    0.08
     прий
    0.08
    oggi
    0.07
    Thrown
    0.07
    тің
    0.07
    Bk
    0.07
    itul
    0.07
     Belle
    0.07
    0.07
    @test
    0.07
    Act Density 0.035%

    No Known Activations