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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section

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

    after Wikipedia edit-related terms

    np_acts-logits-general · gemini-2.0-flash

    authors and metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findOrFail
    -0.44
    \
    -0.41
    stdbool
    -0.41
    …
    -0.40
    dev
    -0.40
    datatables
    -0.40
    ...
    -0.40
    —
    -0.39
    F
    -0.39
    ーと
    -0.38
    POSITIVE LOGITS
     autorytatywna
    1.47
     disambiguazione
    1.15
    :✨
    1.14
     виправивши
    1.12
     beginnetje
    1.08
    rungsseite
    1.07
     bezeichneter
    1.05
     ویکی‌پدی
    1.04
     cherchés
    1.03
     Numerade
    1.03
    Act Density 0.201%

    No Known Activations