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

    Neuronpedia

    INDEX
    Explanations

    events and dates

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric expressions and related tokens (e.g., dates, counts, measurements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Parcel
    -0.07
     Scratch
    -0.06
     ise
    -0.06
     FileInfo
    -0.06
    кут
    -0.06
     Then
    -0.06
     antigen
    -0.06
     Carousel
    -0.06
    asıyla
    -0.06
    εφ
    -0.06
    POSITIVE LOGITS
    ७
    0.07
    _two
    0.06
    <L
    0.06
     dopo
    0.06
    _city
    0.06
    ика
    0.06
     még
    0.06
    RACT
    0.06
    지노
    0.06
    (Html
    0.06
    Act Density 0.028%

    No Known Activations