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

    Neuronpedia

    INDEX
    Explanations

    Russian code-related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    decorators
    -0.07
     disciplined
    -0.07
    WINDOWS
    -0.07
    옳
    -0.07
    //-----------------------------------------------------------------------------↵
    -0.07
    YL
    -0.07
    спект
    -0.07
    /R
    -0.07
    זכ
    -0.06
    新手
    -0.06
    POSITIVE LOGITS
    -con
    0.07
    推送
    0.07
    表面
    0.07
     happened
    0.06
    tron
    0.06
     much
    0.06
    宫
    0.06
    棒
    0.06
    光芒
    0.06
     be
    0.06
    Act Density 0.112%

    No Known Activations