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

    Neuronpedia

    INDEX
    Explanations

    US politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     branch
    -0.07
    parts
    -0.06
     thieves
    -0.06
     updating
    -0.06
     مرتب
    -0.06
     BC
    -0.06
     seul
    -0.06
     vicinity
    -0.06
    zej
    -0.06
    browser
    -0.06
    POSITIVE LOGITS
     znač
    0.08
     cerv
    0.07
    idine
    0.06
    VERTISE
    0.06
    isposable
    0.06
     tăng
    0.06
     fare
    0.06
    /'.$
    0.06
    :both
    0.06
    ($('#
    0.06
    Act Density 0.024%

    No Known Activations