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

    Neuronpedia

    INDEX
    Explanations

    Legal opinions

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric legal citations and rule references (e.g., statute or court‐rule numbers and their decimal fragments).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     wich
    -0.06
     ierr
    -0.06
     흔
    -0.06
    Row
    -0.06
    (book
    -0.06
    Tor
    -0.06
    єте
    -0.06
    机场
    -0.05
    .faceVertexUvs
    -0.05
    _',
    -0.05
    POSITIVE LOGITS
    JO
    0.06
     betrayal
    0.06
     Dương
    0.06
     Agu
    0.06
     bowling
    0.06
     ofApp
    0.06
     J
    0.06
     ale
    0.06
     نقش
    0.06
    -access
    0.06
    Act Density 0.000%

    No Known Activations