INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     городской
    -0.09
     indoor
    -0.08
     подня
    -0.08
     कल्प
    -0.08
     monumental
    -0.08
     серед
    -0.08
     всю
    -0.07
    stav
    -0.07
    Indoor
    -0.07
    -0.07
    POSITIVE LOGITS
     homolog
    0.08
     Quick
    0.07
    Quick
    0.07
     nass
    0.07
     gh
    0.07
     moj
    0.07
     appropr
    0.07
     genet
    0.07
    επισ
    0.07
    vest
    0.07
    Act Density 0.001%

    No Known Activations