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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     methodName
    -0.06
     compare
    -0.06
     дорож
    -0.06
     مرد
    -0.06
     problémy
    -0.06
     открыт
    -0.06
    امی
    -0.06
     mapper
    -0.06
    画
    -0.06
    .leading
    -0.06
    POSITIVE LOGITS
    .setUp
    0.07
    big
    0.07
    tep
    0.07
    mun
    0.07
    )‏
    0.07
    -Re
    0.07
    िण
    0.07
    äre
    0.07
    _outline
    0.07
    split
    0.06
    Act Density 0.121%

    No Known Activations