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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash

    This neuron detects references to collective entities or societal groups, such as “people,” “government,” or similar terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     car
    -0.07
    兼
    -0.07
    콜걸
    -0.07
     افزایش
    -0.07
     surrogate
    -0.07
    Marco
    -0.06
     dinosaur
    -0.06
    .oper
    -0.06
    itch
    -0.06
    irates
    -0.06
    POSITIVE LOGITS
     People
    0.09
     PEOPLE
    0.09
     peoples
    0.08
    人民
    0.08
    Messaging
    0.07
     hep
    0.07
    たちの
    0.07
     vulgar
    0.07
     Lebanese
    0.06
     halk
    0.06
    Act Density 0.016%

    No Known Activations