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 responds to temporal sequencing cues—particularly words like “late,” “later,” and “last” that mark shifts in time.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    求购
    -0.07
    ImagePath
    -0.07
    (indexPath
    -0.06
    getOrElse
    -0.06
    _algorithm
    -0.06
     sempre
    -0.06
    	display
    -0.06
     educator
    -0.06
     gris
    -0.06
    .match
    -0.06
    POSITIVE LOGITS
    Esp
    0.07
    ertas
    0.07
    enge
    0.07
     ПО
    0.06
    exc
    0.06
    veled
    0.06
     Voyage
    0.06
    мет
    0.06
    �
    0.06
    �
    0.06
    Act Density 0.108%

    No Known Activations