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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific research, medical terms, and their associated jargon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns, titles, medical/scientific terms

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

    finds technical, domain-specific tokens and named entities typical of scientific/academic writing.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     ๆ
    -0.53
     مشين
    -0.52
     propOrder
    -0.52
     فريبيس
    -0.49
     jScrollPane
    -0.49
     parseFrom
    -0.49
     linkovi
    -0.49
     unknownFields
    -0.49
    awtextra
    -0.48
     partite
    -0.47
    POSITIVE LOGITS
     nonUne
    0.62
    ----</
    0.49
    Manbalar
    0.47
     Monfieur
    0.47
    TryDecodeAsNil
    0.44
    ‌شده
    0.44
    };*/
    0.43
    filepath
    0.42
    setContentView
    0.41
    ofthe
    0.41
    Act Density 6.962%

    No Known Activations