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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash

    the starts of section headings or titles (tokens that mark section headers, titles, or other structural/document headings).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    oker
    -0.07
    ीम
    -0.07
     Office
    -0.07
     apiUrl
    -0.07
    _tool
    -0.06
    游
    -0.06
    菜
    -0.06
    /ip
    -0.06
    ่อ
    -0.06
    .NODE
    -0.06
    POSITIVE LOGITS
    urable
    0.07
    .Named
    0.07
     wsp
    0.06
    .put
    0.06
    .Username
    0.06
     maliyet
    0.06
    输出
    0.06
     Obs
    0.06
     şüph
    0.06
     '.'
    0.06
    Act Density 16.336%

    No Known Activations