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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    This neuron detects legal document headings and entity names, such as court names, parties, and case identifiers in litigation filings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ол
    -0.06
    <number
    -0.06
    INVALID
    -0.06
    aud
    -0.06
    PO
    -0.06
    Lesson
    -0.06
     utilities
    -0.06
    Richard
    -0.06
    _WIDGET
    -0.06
    收入
    -0.05
    POSITIVE LOGITS
     responders
    0.07
     responder
    0.07
     Dj
    0.07
     comprehensive
    0.07
     capable
    0.07
    특별
    0.07
    faction
    0.06
     jeder
    0.06
     albeit
    0.06
    RIA
    0.06
    Act Density 0.014%

    No Known Activations