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

    Neuronpedia

    INDEX
    Explanations

    past events

    np_max-act · gemini-2.0-flash

    The neuron flags numeric tokens—dates, scores, percentages, and other number-related mentions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Subject
    -0.07
     ]).
    -0.07
     Cindy
    -0.07
    asına
    -0.06
    	emit
    -0.06
    ocurrency
    -0.06
    _indicator
    -0.06
    .WRAP
    -0.06
    other
    -0.06
     århus
    -0.06
    POSITIVE LOGITS
    qq
    0.08
    ¨¨
    0.07
    /LICENSE
    0.07
     Tr
    0.07
    (↵↵
    0.06
     srand
    0.06
    》，
    0.06
     лег
    0.06
    ,</
    0.06
     &___
    0.06
    Act Density 0.028%

    No Known Activations