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

    Neuronpedia

    INDEX
    Explanations

    registry

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the Windows registry (e.g., “registry,” “regedit,” or references to registry keys).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     اند
    -0.06
    .Employee
    -0.06
    UDENT
    -0.06
    .paint
    -0.06
     Pelosi
    -0.06
     варі
    -0.06
    _hand
    -0.06
    oncé
    -0.06
     nau
    -0.06
     цвет
    -0.06
    POSITIVE LOGITS
     thảo
    0.08
    Orders
    0.07
    estead
    0.07
     طبقه
    0.07
    스터
    0.06
     enjoyable
    0.06
     Senators
    0.06
     relations
    0.06
     Legislative
    0.06
     dziewcz
    0.06
    Act Density 0.003%

    No Known Activations