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

    Neuronpedia

    INDEX
    Explanations

    Facebook software/AI usage

    np_max-act-logits · gemini-2.0-flash

    instances where the assistant refers to itself as an AI (e.g., "As an AI language model").

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
    sten
    -0.07
    _swap
    -0.06
    люч
    -0.06
    иц
    -0.06
    etty
    -0.06
    userid
    -0.06
     protestors
    -0.06
     demonstrates
    -0.06
    зации
    -0.06
    Username
    -0.06
    POSITIVE LOGITS
     arbit
    0.07
    нівер
    0.07
    获得
    0.07
     универ
    0.07
     Turning
    0.07
    odon
    0.06
    .Word
    0.06
    0.06
    etchup
    0.06
     //////////
    0.06
    Act Density 0.018%

    No Known Activations