INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     dolo
    -0.08
     Eleg
    -0.08
     iya
    -0.08
    ign
    -0.07
     prec
    -0.07
     evaporation
    -0.07
     Gray
    -0.07
     incense
    -0.07
    -0.07
    iski
    -0.07
    POSITIVE LOGITS
    0.08
     перест
    0.08
    0.08
     Pun
    0.08
    0.08
    unders
    0.07
    inte
    0.07
    placer
    0.07
    Пер
    0.07
     Kob
    0.07
    Act Density 0.011%

    No Known Activations