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

    Neuronpedia

    INDEX
    Explanations

    Code/Markup

    np_max-act · gemini-2.0-flash

    The neuron fires on Markdown-style section headers (e.g. lines beginning with “##”, “###”, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Tampa
    -0.06
     Mozart
    -0.06
     Maggie
    -0.06
    Corner
    -0.06
    TYPE
    -0.06
    Desde
    -0.06
    team
    -0.06
    IconButton
    -0.06
    Mix
    -0.06
     grapes
    -0.06
    POSITIVE LOGITS
     societal
    0.07
    (土
    0.07
    ?
    0.07
     ملي
    0.07
    ёр
    0.06
     อำเภ
    0.06
     아
    0.06
     встанов
    0.06
    uição
    0.06
    召
    0.06
    Act Density 0.042%

    No Known Activations