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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acent
    -0.07
    :n
    -0.06
     dicho
    -0.06
    detalle
    -0.06
    ror
    -0.06
    <boolean
    -0.06
    /in
    -0.06
     disin
    -0.06
    _sale
    -0.06
    jab
    -0.06
    POSITIVE LOGITS
     OTHER
    0.16
    냐
    0.08
    ubah
    0.07
     aldı
    0.06
     stylesheet
    0.06
     allies
    0.06
    입니다
    0.06
     performans
    0.06
    other
    0.06
    ë
    0.06
    Act Density 0.003%

    No Known Activations