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

    Neuronpedia

    INDEX
    Explanations

    references to legal or formal documents and titles

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

    Tokens preceding people's names/titles

    np_acts-logits-general · gemini-2.0-flash

    names and titles of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sarkozy
    -0.65
     Gertrude
    -0.64
     Camila
    -0.63
     Lucille
    -0.60
     Sylvie
    -0.60
     Minato
    -0.59
     Mahabhar
    -0.59
     Ichigo
    -0.59
    ียบ
    -0.58
    Camila
    -0.57
    POSITIVE LOGITS
     John
    0.78
     David
    0.65
    rawDesc
    0.65
     wireType
    0.64
     насељу
    0.61
    CodeAttribute
    0.61
     Richard
    0.61
     Dr
    0.60
    gameserver
    0.59
     newcomer
    0.59
    Act Density 1.309%

    No Known Activations