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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    function words and punctuation that link or structure clauses and sentences, signaling coordination, transitions, and question/quotation boundaries.

    oai_token-act-pair · gpt-5Triggered by @faiazazmain99

    formal written text, particularly punctuation and conjunctions in news articles or technical documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @faiazazmain99

    comma-separated lists, item enumeration, and sequential parallel structures.

    oai_token-act-pair · claude-4-5-haikuTriggered by @faiazazmain99
    New Auto-Interp
    Negative Logits
     impres
    -0.29
    æ¿Ģåıij
    -0.27
     runes
    -0.27
    oen
    -0.26
    rian
    -0.25
    èį£
    -0.25
    è§Ĥæµĭ
    -0.25
    åħīèį£
    -0.24
    åij½é¢ĺ
    -0.24
    hd
    -0.24
    POSITIVE LOGITS
    евиÑĩ
    0.28
    bay
    0.28
    emy
    0.27
    é¦Ĩ
    0.26
    lice
    0.26
     Hubb
    0.26
    RELATED
    0.25
    ±Ð¾ÑĤ
    0.25
    _https
    0.25
    serv
    0.25
    Act Density 21.084%

    No Known Activations