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

    Neuronpedia

    INDEX
    Explanations

    legal text

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on the numeric and reporter‐abbreviation elements of legal case citations (e.g. volume/page numbers and things like “N.W.,” “Pac.,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    legal terminologies and concepts associated with court cases and legal proceedings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ived
    -0.07
    memberOf
    -0.07
    เหน
    -0.07
     ruta
    -0.07
    出
    -0.07
     salt
    -0.07
     startIndex
    -0.07
     іс
    -0.06
     murdered
    -0.06
    ятно
    -0.06
    POSITIVE LOGITS
    -G
    0.07
    onomous
    0.06
     gł
    0.06
     improperly
    0.06
    [section
    0.06
     Wildcats
    0.06
     reporters
    0.06
    Drug
    0.06
     Tacoma
    0.06
     Agr
    0.06
    Act Density 0.001%

    No Known Activations