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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash

    machine-readable structured data and markup/code syntax (e.g., tags, attributes, schemas, and closing delimiters) rather than natural-language prose.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Sioux
    -0.08
    栏目
    -0.08
    这两年
    -0.07
    祥
    -0.07
    .amazon
    -0.07
     Boxing
    -0.07
    ือน
    -0.07
    ᐕ
    -0.07
     Braun
    -0.06
     Wald
    -0.06
    POSITIVE LOGITS
    big
    0.07
     arise
    0.07
     pamię
    0.06
    เศร
    0.06
    삳
    0.06
    依据
    0.06
    付款
    0.06
    Chi
    0.06
    (Window
    0.06
    .CurrentCulture
    0.06
    Act Density 0.070%

    No Known Activations