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

    Neuronpedia

    INDEX
    Explanations

    abortion

    np_max-act · gemini-2.0-flash

    The neuron fires on domain-specific or technical nouns (specialized jargon) typically found in formal headings or academic/scientific contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    specialized scientific and technical terminology, especially biomedical terms and hyphenated compound nouns.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     recommended
    -0.07
     έως
    -0.06
    SQLite
    -0.06
    uktur
    -0.06
    anki
    -0.06
     \"
    -0.06
     ////
    -0.06
     tội
    -0.06
     ตำบล
    -0.06
     jewellery
    -0.06
    POSITIVE LOGITS
    ieces
    0.07
    먹
    0.07
    NEY
    0.07
     anderen
    0.06
     není
    0.06
    اوند
    0.06
    <TKey
    0.06
    оян
    0.06
    veled
    0.06
    <GameObject
    0.06
    Act Density 0.534%

    No Known Activations