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

    Neuronpedia

    INDEX
    Explanations

    proper names or specific entities associated with notable individuals

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

    Words/characters with diacritics/accent marks

    np_acts-logits-general · gemini-2.0-flash

    Māori, Québec, French, Icelandic, Sanskrit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     --
    -0.88
     ----
    -0.65
     -----
    -0.64
    "--
    -0.64
     ------
    -0.61
     ---
    -0.61
    )--
    -0.61
     -------
    -0.61
     __
    -0.59
    --"
    -0.59
    POSITIVE LOGITS
     résumé
    0.74
     Māori
    0.72
     Québec
    0.70
     cafés
    0.70
     Citroën
    0.70
     Montréal
    0.69
     élite
    0.69
     purée
    0.67
     rôle
    0.67
     ín
    0.65
    Act Density 2.769%

    No Known Activations