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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash

    first-person self-references, indicating first-person narration.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    еру
    -0.07
     getList
    -0.07
    ounsel
    -0.06
    .adapter
    -0.06
    _PARAM
    -0.06
    ModelState
    -0.06
    诺
    -0.06
    olars
    -0.06
    -ms
    -0.06
    sam
    -0.06
    POSITIVE LOGITS
    —↵↵
    0.07
     gadgets
    0.07
     gemeins
    0.07
     Sega
    0.07
     сбор
    0.07
     сили
    0.07
     Bri
    0.06
    .&
    0.06
    ?<
    0.06
    \Context
    0.06
    Act Density 0.061%

    No Known Activations