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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens (dates, counts, measurements, and other numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     RENDER
    -0.07
     Choose
    -0.07
    [path
    -0.06
    VIEW
    -0.06
    FAST
    -0.06
     muscle
    -0.06
    (up
    -0.06
     entertaining
    -0.06
    _smart
    -0.06
    _Thread
    -0.06
    POSITIVE LOGITS
    ynch
    0.07
     мат
    0.07
    搬
    0.06
    、本
    0.06
    /sl
    0.06
    ở
    0.06
    işi
    0.06
    本
    0.06
     propio
    0.06
    _Native
    0.06
    Act Density 0.091%

    No Known Activations