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

    Neuronpedia

    INDEX
    Explanations

    Chinese last names

    np_max-act · gemini-2.0-flash

    The neuron activates on author names (and year/number tags) in scholarly citation references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     EnumerableStream
    -0.08
    Craig
    -0.06
     iid
    -0.06
     erg
    -0.06
    ős
    -0.06
     Craig
    -0.06
     extrav
    -0.06
     zar
    -0.06
    ep
    -0.05
    Kel
    -0.05
    POSITIVE LOGITS
     -*
    0.09
    JA
    0.07
     awaited
    0.07
     století
    0.07
     Mai
    0.07
    projects
    0.07
    <m
    0.07
    	hash
    0.06
     Garcia
    0.06
    smith
    0.06
    Act Density 0.015%

    No Known Activations