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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron fires on the header metadata of court opinions—specifically on dates, jurisdictions, and place names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     aggressively
    -0.07
    His
    -0.06
    .UseFont
    -0.06
    Our
    -0.06
    ardi
    -0.06
    Generator
    -0.06
     commentators
    -0.06
     Word
    -0.06
    See
    -0.06
    黒
    -0.06
    POSITIVE LOGITS
     scholarly
    0.07
    deniz
    0.06
    luluk
    0.06
     �
    0.06
     WALL
    0.06
     Bands
    0.06
     βο
    0.06
    .par
    0.06
     соответ
    0.06
    溪
    0.06
    Act Density 0.020%

    No Known Activations