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

    Neuronpedia

    INDEX
    Explanations

    section

    np_max-act · gemini-2.0-flash

    The neuron detects references to legal filings, especially mentions of statute or section numbers and related legal terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Adds
    -0.07
    ウェ
    -0.07
    requ
    -0.07
    ạc
    -0.07
    _ctxt
    -0.07
     gé
    -0.07
    VisualStyle
    -0.07
     equalTo
    -0.06
    การณ
    -0.06
    .dtype
    -0.06
    POSITIVE LOGITS
    September
    0.06
    *))
    0.06
    October
    0.06
    tober
    0.06
     içerisinde
    0.06
     October
    0.06
     Barr
    0.06
    _join
    0.06
     professionnel
    0.06
     September
    0.06
    Act Density 0.006%

    No Known Activations