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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cheiden
    -0.08
    ingen
    -0.08
    镇江
    -0.07
    ент
    -0.07
    شكر
    -0.07
     strikeouts
    -0.07
    擁有
    -0.07
    ỷ
    -0.07
    Journal
    -0.07
     chociaż
    -0.07
    POSITIVE LOGITS
    亢
    0.07
    _lastname
    0.07
    SERVER
    0.07
    _open
    0.07
     booth
    0.06
    大胆
    0.06
    生物科技
    0.06
    ]]
    0.06
     gemeins
    0.06
    羔
    0.06
    Act Density 0.007%

    No Known Activations