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

    Neuronpedia

    INDEX
    Explanations

    United

    np_max-act · gemini-2.0-flash

    The neuron detects the formal header lines of U.S. federal appellate court opinions (e.g. “United States Court of Appeals” and related docket metadata).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /tos
    -0.08
    (pub
    -0.06
    '+
    -0.06
    Oh
    -0.06
     reservation
    -0.06
     گیر
    -0.06
    (ref
    -0.06
    riority
    -0.06
     sea
    -0.06
    justify
    -0.06
    POSITIVE LOGITS
     CLLocation
    0.07
    ζει
    0.07
     ihtiyaç
    0.07
     maxim
    0.06
     rebellion
    0.06
    無し�
    0.06
     чит
    0.06
    .firebaseapp
    0.06
    batis
    0.06
    .month
    0.06
    Act Density 0.006%

    No Known Activations