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

    Neuronpedia

    INDEX
    Explanations

    ued

    np_max-act · gemini-2.0-flash

    This neuron detects the “ARGUED” heading (and related date‐label tokens) in a court‐opinion metadata block.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     receipt
    -0.08
     payer
    -0.06
    ETING
    -0.06
    /dist
    -0.06
    سوب
    -0.06
    asts
    -0.06
     présent
    -0.06
     /*#__
    -0.06
     згод
    -0.06
     सच
    -0.06
    POSITIVE LOGITS
    ']);
    0.07
     أق
    0.07
    วงศ
    0.06
     outsider
    0.06
     locations
    0.06
    SN
    0.06
     negotiated
    0.06
    _archive
    0.05
    .Health
    0.05
     externally
    0.05
    Act Density 0.001%

    No Known Activations