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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    sentences where the user asks for help/advice or otherwise makes a direct request (e.g., "Can you...?", "What should I do...?").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    gars
    -0.07
    GINE
    -0.07
    acement
    -0.07
    hop
    -0.07
    ares
    -0.06
    ErrorHandler
    -0.06
    really
    -0.06
     nasty
    -0.06
    krvldkf
    -0.06
    getEmail
    -0.06
    POSITIVE LOGITS
     LDS
    0.06
     epis
    0.06
    CAR
    0.06
    \uC
    0.06
    .offer
    0.06
    (IT
    0.05
     Wants
    0.05
    scala
    0.05
    .getS
    0.05
     Delta
    0.05
    Act Density 0.054%

    No Known Activations