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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    This neuron detects legal citation elements, such as case numbers, statute sections, and court‐rule references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    密
    -0.07
    ownt
    -0.06
    _tweets
    -0.06
     Wick
    -0.06
    unted
    -0.06
    гал
    -0.06
     stocking
    -0.06
     Κα
    -0.06
    DEPEND
    -0.06
    .VAL
    -0.06
    POSITIVE LOGITS
    _basis
    0.07
     asbestos
    0.06
    .Right
    0.06
    PECT
    0.06
     Vaccine
    0.06
    (nr
    0.06
     Lana
    0.06
     uid
    0.06
    ná
    0.06
    0.06
    Act Density 0.002%

    No Known Activations