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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens in user queries asking for the current time in a location, especially the words “time” and “in.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     internship
    -0.07
     Gram
    -0.07
     Kia
    -0.06
    れた
    -0.06
     Lear
    -0.06
     Match
    -0.06
    (find
    -0.06
    _mi
    -0.06
     kick
    -0.06
     Cards
    -0.05
    POSITIVE LOGITS
    ỗng
    0.07
     microwave
    0.07
    CLUDED
    0.06
     '!
    0.06
     піс
    0.06
    OOSE
    0.06
    ptrdiff
    0.06
    působ
    0.06
    Solar
    0.06
     apa
    0.06
    Act Density 0.006%

    No Known Activations