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

    Neuronpedia

    INDEX
    Explanations

    past roles

    np_max-act · gemini-2.0-flash

    The neuron fires on language detailing a person’s career roles and timeline (e.g. “previously served as,” “provided,” job titles and date ranges).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     EVENTS
    -0.08
    840
    -0.07
    έν
    -0.06
     curtain
    -0.06
     کر
    -0.06
     کو
    -0.06
     turf
    -0.06
     kulak
    -0.06
     Arm
    -0.06
    中國
    -0.06
    POSITIVE LOGITS
     تفس
    0.07
    ören
    0.07
     birey
    0.06
    (be
    0.06
     telefon
    0.06
    habi
    0.06
    ->{'
    0.06
    ذا
    0.06
    issuer
    0.06
    ؟
    0.06
    Act Density 0.029%

    No Known Activations