Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Russian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urse
    -0.07
     billionaires
    -0.07
    restriction
    -0.06
     faction
    -0.06
    ær
    -0.06
    라
    -0.06
    _feats
    -0.06
    monitor
    -0.06
    ोग
    -0.06
     Throwable
    -0.06
    POSITIVE LOGITS
     dejting
    0.07
     znám
    0.07
     okres
    0.06
     транс
    0.06
    ITS
    0.06
     McCartney
    0.06
     learnt
    0.06
     perk
    0.06
    maktadır
    0.06
     مقد
    0.06
    Act Density 0.003%

    No Known Activations