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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens—digits, numbers, and numeric references—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     شن
    -0.07
    Ki
    -0.07
    PLUS
    -0.07
    Boundary
    -0.06
     суспіль
    -0.06
     vự
    -0.06
    ///
    -0.06
    ानन
    -0.06
    κού
    -0.06
     خدا
    -0.06
    POSITIVE LOGITS
    -cons
    0.07
    Tweet
    0.06
    cısı
    0.06
     deber
    0.06
     Date
    0.06
    /rest
    0.06
    TabIndex
    0.06
     вне
    0.06
     Bey
    0.06
    \Message
    0.06
    Act Density 0.053%

    No Known Activations