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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash

    tokens from the user's messages (i.e., user-turn tokens/questions).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    Rua
    -0.07
    串
    -0.07
    craper
    -0.07
    redi
    -0.06
    OUSE
    -0.06
    .raise
    -0.06
    _NOP
    -0.06
    ounded
    -0.06
    族
    -0.06
     Fairy
    -0.06
    POSITIVE LOGITS
    	img
    0.07
    comments
    0.07
    	err
    0.07
     liberalism
    0.06
    _sid
    0.06
     enhance
    0.06
     affiliates
    0.06
    	Expect
    0.06
     schnell
    0.06
     leicht
    0.06
    Act Density 1.264%

    No Known Activations