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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash

    first-person self-referential language, especially collective or possessive references to the author or their group.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     pazar
    -0.06
    _space
    -0.06
    .if
    -0.06
    .decoder
    -0.06
     울
    -0.06
    벨
    -0.06
     atual
    -0.06
    งต
    -0.06
     mesel
    -0.05
    侯
    -0.05
    POSITIVE LOGITS
     Mushroom
    0.07
     shipped
    0.07
    んど
    0.07
     báo
    0.06
    ernen
    0.06
     유저
    0.06
    |M
    0.06
     serão
    0.06
     abstraction
    0.06
    )[-
    0.06
    Act Density 0.147%

    No Known Activations