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

    Neuronpedia

    INDEX
    Explanations

    Legal documents

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on docket or case‐number identifiers (e.g. the “No.” preceding the case number).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    人才
    -0.07
     cui
    -0.06
     Notices
    -0.06
    _analysis
    -0.06
    крет
    -0.06
     업
    -0.06
     coincidence
    -0.06
    nict
    -0.06
     mate
    -0.06
     관계
    -0.06
    POSITIVE LOGITS
    How
    0.07
    ?↵
    0.07
    estimated
    0.06
     germany
    0.06
     Urdu
    0.06
     whistleblower
    0.06
     требует
    0.06
    Loaded
    0.06
    _<?
    0.06
     Recommend
    0.06
    Act Density 0.002%

    No Known Activations