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

    Neuronpedia

    INDEX
    Explanations

    job titles

    np_max-act · gemini-2.0-flash

    The neuron responds to words denoting an authority figure or leader (e.g. “chieftain,” “headmaster”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     estimated
    -0.07
    載
    -0.06
    .setDefault
    -0.06
     Walnut
    -0.06
    _city
    -0.06
    事
    -0.06
    Binder
    -0.06
    _device
    -0.06
     vå
    -0.05
     استخدام
    -0.05
    POSITIVE LOGITS
     망
    0.07
     //<
    0.07
     olan
    0.07
     长
    0.07
     (!_
    0.07
    šení
    0.07
     ★
    0.07
     žal
    0.07
     体
    0.06
    ,,,
    0.06
    Act Density 0.032%

    No Known Activations