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

    Neuronpedia

    INDEX
    Explanations

    utility regulation

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of official bodies and agencies (e.g. regulatory commissions, courts, intervenors) in legal text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     harmless
    -0.07
     destroys
    -0.06
    )"},↵
    -0.06
     Nunes
    -0.06
    istrovství
    -0.06
     interactions
    -0.06
    aría
    -0.06
    ARENT
    -0.06
     mnohem
    -0.06
    .webdriver
    -0.06
    POSITIVE LOGITS
     setPosition
    0.07
     spans
    0.07
     cores
    0.06
     Yellowstone
    0.06
     thay
    0.06
    aligned
    0.06
    Pose
    0.06
     commonplace
    0.06
    .alignment
    0.06
    ále
    0.06
    Act Density 0.011%

    No Known Activations