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

    Neuronpedia

    INDEX
    Explanations

    -p

    np_max-act · gemini-2.0-flash

    The neuron fires on date‐ and time‐related tokens (e.g. numeric year/month/day stamps, “HH:MM” time formats, “GMT,” and other timestamp metadata).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     happier
    -0.06
    -0.06
     esse
    -0.06
    роме
    -0.06
    berries
    -0.06
     seas
    -0.06
     peanut
    -0.06
    .mean
    -0.06
     canyon
    -0.06
     ساختمان
    -0.06
    POSITIVE LOGITS
     Верхов
    0.07
     seleccion
    0.07
     náklady
    0.06
    ائج
    0.06
    読
    0.06
    Cy
    0.06
    にと
    0.06
    Clientes
    0.06
    _TextChanged
    0.06
    の中
    0.06
    Act Density 0.019%

    No Known Activations