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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    assistant responses and explanatory, tutorial-style content (including assistant role markers and instructional phrasing).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    异常
    -0.07
     전
    -0.06
    	on
    -0.06
    .sd
    -0.06
    .af
    -0.06
     请求
    -0.06
     Mét
    -0.06
     состоя
    -0.06
    /url
    -0.06
    _condition
    -0.06
    POSITIVE LOGITS
     А
    0.07
     alphabet
    0.07
    '])->
    0.07
     market
    0.07
    heit
    0.07
    bsites
    0.07
     torchvision
    0.07
    _STACK
    0.06
     Businesses
    0.06
    'nun
    0.06
    Act Density 0.126%

    No Known Activations