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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron detects references to statutes and legal provisions (e.g. mentions of an Act, its sections, and the year).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     humanity
    -0.07
     descriptions
    -0.06
     resolve
    -0.06
    _context
    -0.06
    ูตร
    -0.06
    .currentTime
    -0.06
    _map
    -0.06
    inizin
    -0.06
     monster
    -0.06
     сті
    -0.06
    POSITIVE LOGITS
     Includes
    0.07
     EXISTS
    0.07
    ایج
    0.06
    .TIM
    0.06
    міністра
    0.06
    loven
    0.06
     �
    0.06
     втра
    0.06
    VERN
    0.06
     Implements
    0.06
    Act Density 0.011%

    No Known Activations