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

    Neuronpedia

    INDEX
    Explanations

    organizations and positions

    np_max-act · gemini-2.0-flash

    The neuron detects references to organizational or governmental leadership titles (e.g. Council, Mayors, Director, President).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    PK
    -0.06
    _ASSERT
    -0.06
    _bus
    -0.06
    -op
    -0.06
     ท
    -0.06
    벌
    -0.06
    Airport
    -0.06
    -existing
    -0.06
     قائمة
    -0.06
     pause
    -0.06
    POSITIVE LOGITS
    _guid
    0.07
    ="?
    0.07
     Fundamental
    0.06
     Stable
    0.06
    ervatives
    0.06
    .legend
    0.06
     Synd
    0.06
    관리자
    0.06
    _validate
    0.06
     öğretmen
    0.06
    Act Density 0.077%

    No Known Activations