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

    Neuronpedia

    INDEX
    Explanations

    Software specifications/documentation

    np_max-act · gemini-2.0-flash

    self-referential boilerplate where the assistant identifies itself as an AI language model and describes its capabilities or limitations.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     broccoli
    -0.08
     resembl
    -0.07
    James
    -0.07
    Im
    -0.07
    禀
    -0.07
    落实
    -0.07
     nowrap
    -0.07
    ilee
    -0.06
    的形式
    -0.06
    _USERS
    -0.06
    POSITIVE LOGITS
     dna
    0.07
     Paladin
    0.07
    dna
    0.07
     Rohing
    0.07
    低迷
    0.07
     Damn
    0.07
    фор
    0.07
    	direction
    0.07
     маст
    0.07
    滑雪
    0.07
    Act Density 0.017%

    No Known Activations