INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ственные
    -0.08
    Path
    -0.08
    _MOV
    -0.07
     MacOS
    -0.07
     Neg
    -0.07
     Run
    -0.07
     noticeably
    -0.07
    -built
    -0.07
    fire
    -0.07
     děti
    -0.07
    POSITIVE LOGITS
     port
    0.08
     ports
    0.08
     Port
    0.07
     Ports
    0.06
    _hs
    0.06
     руб
    0.06
     findOne
    0.06
    .Localization
    0.06
    gıç
    0.06
     bouts
    0.06
    Act Density 0.008%

    No Known Activations