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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters indicating segments or structures within a coding context

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

    page manager, page_small_text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.42
    Autowired
    -0.39
    Trusted
    -0.38
     finas
    -0.38
     trustworthy
    -0.36
     necessárias
    -0.36
     sanat
    -0.36
     forças
    -0.36
    的模样
    -0.36
    SneakyThrows
    -0.35
    POSITIVE LOGITS
     Pages
    0.85
     Page
    0.84
     getPage
    0.84
    getPage
    0.84
     PAGES
    0.81
    setPage
    0.79
     page
    0.77
    Page
    0.77
    Pages
    0.75
     pages
    0.74
    Act Density 0.006%

    No Known Activations