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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect numerical legal references (section, statute, and case citation numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    CHK
    -0.07
    假
    -0.06
     womb
    -0.06
     Rek
    -0.06
    .attrs
    -0.06
    룡
    -0.06
     米
    -0.06
    -gr
    -0.06
    ीत
    -0.06
    #ifndef
    -0.06
    POSITIVE LOGITS
    TRACE
    0.07
    /**
↵
    0.06
     wes
    0.06
     thous
    0.06
    .Buffered
    0.06
     target
    0.06
     Monument
    0.06
     terrorist
    0.06
    aceut
    0.06
     Politico
    0.06
    Act Density 0.007%

    No Known Activations