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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wildcard
    -0.08
    [curr
    -0.07
     Vice
    -0.07
    <Cell
    -0.07
    getNext
    -0.07
     innocent
    -0.06
    !"↵↵
    -0.06
    _square
    -0.06
    pkt
    -0.06
    buffers
    -0.06
    POSITIVE LOGITS
    oteric
    0.06
    услов
    0.06
    //*[@
    0.06
    acağı
    0.06
     neoliberal
    0.06
    اهيم
    0.06
     Eaton
    0.06
    ава
    0.06
     모
    0.06
    ‌های
    0.06
    Act Density 0.000%

    No Known Activations