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

    Neuronpedia

    INDEX
    Explanations

    people's names

    np_max-act · gemini-2.0-flash

    This neuron detects personal surnames—i.e., capitalized family names in biographical entries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    128
    -0.07
    cken
    -0.06
    (builder
    -0.06
    trusted
    -0.06
    .ph
    -0.06
    126
    -0.06
    UILDER
    -0.06
    47
    -0.06
     지원
    -0.06
    .Butter
    -0.05
    POSITIVE LOGITS
    ickém
    0.07
     taxonomy
    0.07
    เหต
    0.07
    -logo
    0.07
     clk
    0.06
    .WriteHeader
    0.06
     orderby
    0.06
     مستق
    0.06
     rgba
    0.06
     Hebrew
    0.06
    Act Density 0.037%

    No Known Activations