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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    Named entities and specific proper nouns (people, places, organizations, product/model names and technical terms).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ै?↵
    -0.07
    ैं।↵
    -0.06
    ,...↵
    -0.06
     сосуд
    -0.06
    agged
    -0.06
    chod
    -0.06
     合
    -0.06
    actly
    -0.06
    isen
    -0.06
    invalid
    -0.06
    POSITIVE LOGITS
    CodeAt
    0.07
    เก
    0.07
    �
    0.06
     Mr
    0.06
    _engine
    0.06
    _COOKIE
    0.06
    <ApplicationUser
    0.06
     プ
    0.06
    'A
    0.06
    _MASTER
    0.06
    Act Density 18.528%

    No Known Activations