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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash

    This neuron detects legal case citations, specifically the reporter designator (e.g. the “A” in “925 A.2d 632”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Death
    -0.07
    Death
    -0.07
     widen
    -0.06
    !("{
    -0.06
    _requested
    -0.06
     audiences
    -0.06
    ivicrm
    -0.06
     Vill
    -0.06
     Orlando
    -0.06
    91
    -0.06
    POSITIVE LOGITS
    (pe
    0.07
    �
    0.06
     segundos
    0.06
    (place
    0.06
     contributor
    0.06
     утвержд
    0.06
     огранич
    0.06
     atleast
    0.06
     randomized
    0.06
     Blake
    0.06
    Act Density 0.001%

    No Known Activations