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

    Neuronpedia

    INDEX
    Explanations

    informal writing

    np_max-act · gemini-2.0-flash

    It detects self‑referential, first‑person autobiographical or personal statements (author/narrator speaking about themselves).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    Care
    -0.07
     Navigation
    -0.07
    assin
    -0.06
     Providence
    -0.06
    現
    -0.06
    _inicio
    -0.06
     technical
    -0.06
    mediate
    -0.06
     linear
    -0.06
    wr
    -0.06
    POSITIVE LOGITS
    ='".$
    0.06
    "]);
    0.06
     og
    0.06
    .setTag
    0.06
    UNIT
    0.06
     ガ
    0.06
     тов
    0.06
     autob
    0.06
    .labelX
    0.06
     accepted
    0.06
    Act Density 0.129%

    No Known Activations