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

    Neuronpedia

    INDEX
    Explanations

    Court

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the word “Court” in formal legal headings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Kel
    -0.07
    .assertIn
    -0.06
    )，
    -0.06
    ogs
    -0.06
    .util
    -0.06
    _summary
    -0.06
     abolished
    -0.06
    _builtin
    -0.06
     genomes
    -0.06
    ，因为
    -0.06
    POSITIVE LOGITS
     arşivlendi
    0.07
     fundraising
    0.07
    744
    0.06
    asbourg
    0.06
     CIF
    0.06
     amend
    0.06
    quirrel
    0.06
     sher
    0.06
     lĩnh
    0.06
     jd
    0.06
    Act Density 0.001%

    No Known Activations