INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Fak
    -0.08
    _Record
    -0.08
     fac
    -0.07
    /simple
    -0.07
    Recorder
    -0.07
    -0.07
    iversal
    -0.07
     imper
    -0.07
     Imper
    -0.07
    shi
    -0.07
    POSITIVE LOGITS
     blurred
    0.10
    -bl
    0.08
     PERSON
    0.08
     blurry
    0.08
    ės
    0.08
    0.08
     negatieve
    0.08
    	person
    0.07
    .person
    0.07
    -Bl
    0.07
    Act Density 0.026%

    No Known Activations