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

    Neuronpedia

    INDEX
    Explanations

    demeter & phishing

    np_acts-logits-general · gemini-2.5-flash-lite

    salient named entities and acronyms—proper names, titles, and specialized technical terms that signal key subjects across domains.

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    The neuron activates on enumerated list entries—especially section headings or item titles (e.g. anime character names) in a ranked “waifu” list.

    oai_token-act-pair · o4-miniTriggered by @yooniel31

    user query topics or keywords.

    oai_token-act-pair · deepseek-r1Triggered by @yooniel31
    New Auto-Interp
    Negative Logits
    ৭
    0.16
    ل
    0.16
    rvGroup
    0.15
    name
    0.15
    ناہ
    0.15
    ఫ్
    0.14
     অন্যান্য
    0.14
    کے
    0.14
     ว
    0.14
    ുവരി
    0.14
    POSITIVE LOGITS
    .
    0.19
    ,
    0.18
    。
    0.17
    と呼ばれる
    0.16
    ®,
    0.16
    ®.
    0.15
    :
    0.15
     had
    0.14
    യുടെ
    0.14
    ！
    0.14
    Act Density 10.766%

    No Known Activations