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

    Neuronpedia

    INDEX
    Explanations

    ~

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point numeric values (decimal numbers) appearing in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    <-
    -0.07
    alarını
    -0.07
    xAE
    -0.07
    datal
    -0.07
    patients
    -0.07
    CustomerId
    -0.07
    sport
    -0.07
     beers
    -0.06
    STYLE
    -0.06
     pData
    -0.06
    POSITIVE LOGITS
     обмеж
    0.06
    イ
    0.06
    ữ
    0.06
     soaring
    0.06
     آس
    0.06
     ~
    0.06
    uncios
    0.06
     바이
    0.06
    /live
    0.06
     Randolph
    0.06
    Act Density 0.000%

    No Known Activations