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

    Neuronpedia

    INDEX
    Explanations

    Census

    np_max-act · gemini-2.0-flash

    This neuron primarily responds to mentions of census data (e.g. the word “census” and related numeric year or designation terms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	line
    -0.07
    metadata
    -0.06
     Guru
    -0.06
    відом
    -0.06
    itti
    -0.06
    -money
    -0.06
    	ui
    -0.06
    .colors
    -0.06
    sleep
    -0.06
     ware
    -0.06
    POSITIVE LOGITS
    -bodied
    0.06
    $fields
    0.06
    .Interval
    0.06
    =read
    0.06
    _ylabel
    0.06
     grouping
    0.06
    ,arg
    0.06
    意
    0.06
     крем
    0.06
     Gemini
    0.06
    Act Density 0.001%

    No Known Activations