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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron fires on the header metadata of a court opinion—especially on the judge‐attribution line (the judge’s name and surrounding case‐location/date tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ARGE
    -0.07
     SMART
    -0.07
     宮
    -0.06
     बड
    -0.06
     counselling
    -0.06
    DIR
    -0.06
    dir
    -0.06
     Quart
    -0.06
    _zeros
    -0.06
    اسر
    -0.06
    POSITIVE LOGITS
    ektiv
    0.07
    ขว
    0.06
    might
    0.06
     NUnit
    0.06
    .liferay
    0.06
    ifo
    0.06
     Toastr
    0.06
     Norton
    0.06
     MPH
    0.06
     المدينة
    0.06
    Act Density 0.002%

    No Known Activations