INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     свой
    -0.09
    U
    -0.08
    Ya
    -0.08
     ya
    -0.08
    Stamp
    -0.08
    veyor
    -0.08
     ряд
    -0.08
     school
    -0.07
    UB
    -0.07
    ya
    -0.07
    POSITIVE LOGITS
     uncomp
    0.09
     Category
    0.08
     fingertips
    0.08
     mates
    0.08
     motherhood
    0.08
     adolescence
    0.07
     Neub
    0.07
     प्रक
    0.07
    atsi
    0.07
     komp
    0.07
    Act Density 0.061%

    No Known Activations