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

    Neuronpedia

    INDEX
    Explanations

    javascript code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (IP
    -0.08
    wear
    -0.07
    nm
    -0.07
    质感
    -0.07
    igate
    -0.07
     Establishment
    -0.07
    -conscious
    -0.07
     renovation
    -0.07
    :not
    -0.07
     upp
    -0.07
    POSITIVE LOGITS
    奇迹
    0.06
    遗漏
    0.06
    pl
    0.06
     "}";↵
    0.06
    同
    0.06
    ias
    0.06
    fifo
    0.06
    菍
    0.06
    ']));↵
    0.06
    ię
    0.06
    Act Density 0.016%

    No Known Activations