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

    Neuronpedia

    INDEX
    Explanations

    FILE

    np_max-act · gemini-2.0-flash

    document identifiers and procedural references in legal texts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on the header token “FILE” (as in the “FILED” date line) in court‐document headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    chan
    -0.06
    cid
    -0.06
     melted
    -0.06
    儀
    -0.06
     kd
    -0.06
    仪
    -0.06
    _prepare
    -0.06
     Midnight
    -0.06
     نوف
    -0.06
    oltage
    -0.06
    POSITIVE LOGITS
     Obt
    0.07
     får
    0.07
     δημιουργ
    0.07
    uze
    0.07
    ??↵↵
    0.06
     배우
    0.06
     clr
    0.06
     digging
    0.06
    itories
    0.06
     href
    0.06
    Act Density 0.001%

    No Known Activations