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

    Neuronpedia

    INDEX
    Explanations

    pet

    np_max-act · gemini-2.0-flash

    This neuron spots legal‐citation tokens—abbreviated references to statutes, codes, rules, or case reporters (e.g. “Tex. R. App. P.,” “art. 11.07,” “ref’d”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ря
    -0.07
     τρο
    -0.07
     finest
    -0.07
     material
    -0.06
    민국
    -0.06
     Shaw
    -0.06
    .proto
    -0.06
    丝
    -0.06
     Income
    -0.06
    yme
    -0.06
    POSITIVE LOGITS
     personn
    0.07
    "$
    0.07
    sit
    0.06
     педагог
    0.06
     osg
    0.06
    +'/
    0.06
     persec
    0.06
    _lex
    0.06
     respectful
    0.06
    "},"
    0.06
    Act Density 0.000%

    No Known Activations