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

    Neuronpedia

    INDEX
    Explanations

    days of the week

    np_max-act · gemini-2.0-flash

    This neuron detects date‐header lines by spotting weekday names (e.g. “Wednesday,” “Tuesday,” “Sunday”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     운영
    -0.07
     poměrně
    -0.06
     approximate
    -0.06
     Acer
    -0.06
    	Function
    -0.06
    _activate
    -0.06
     fica
    -0.06
     спад
    -0.06
     випад
    -0.06
    root
    -0.06
    POSITIVE LOGITS
     Equal
    0.06
    $scope
    0.06
     imprison
    0.06
    ele
    0.06
     Income
    0.06
    ằ
    0.06
    ел
    0.06
    _CHARACTER
    0.06
     income
    0.06
    นาง
    0.06
    Act Density 0.004%

    No Known Activations