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 words and phrases that mark repeated or recurring events in time—e.g. “each time,” “every … call,” “subsequent,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	h
    -0.07
    ิธ
    -0.07
    Er
    -0.06
     folded
    -0.06
    าต
    -0.06
     Ker
    -0.06
    Aws
    -0.06
    oreach
    -0.06
    Jason
    -0.06
    spacing
    -0.06
    POSITIVE LOGITS
    =path
    0.06
    .style
    0.06
     everytime
    0.06
    _push
    0.06
    （笑
    0.06
    (Class
    0.06
     POT
    0.06
    /file
    0.06
    .Lerp
    0.06
    Min
    0.06
    Act Density 0.019%

    No Known Activations