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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron detects patent-document citations, i.e. references to “U.S. Pat. No.” and associated patent numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    anager
    -0.07
    .DateFormat
    -0.07
     Fiction
    -0.07
    (provider
    -0.07
     Geld
    -0.06
     …↵↵
    -0.06
     setIs
    -0.06
    .layers
    -0.06
     educator
    -0.06
     missiles
    -0.06
    POSITIVE LOGITS
    см
    0.07
    _noise
    0.07
    lify
    0.07
    AIR
    0.06
    
    0.06
    */),
    0.06
     المص
    0.06
    &);↵
    0.06
    orig
    0.06
     bounced
    0.06
    Act Density 0.014%

    No Known Activations