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

    Neuronpedia

    INDEX
    Explanations

    car

    np_max-act · gemini-2.0-flash

    The neuron responds to the substring “car” (as in parts of words like carotene or carboxylic).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     togg
    -0.06
     Sage
    -0.06
    .endTime
    -0.06
     объ
    -0.06
    =out
    -0.06
     культу
    -0.06
    _intersect
    -0.06
    Nu
    -0.06
    xEE
    -0.06
    .LinkedList
    -0.06
    POSITIVE LOGITS
     CAR
    0.10
    car
    0.10
     Car
    0.09
     car
    0.09
     Carlo
    0.09
    air
    0.09
     Kar
    0.09
     can
    0.09
    CAR
    0.09
     Carol
    0.09
    Act Density 0.023%

    No Known Activations