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

    Neuronpedia

    INDEX
    Explanations

    question mark

    np_max-act · gemini-2.0-flash

    questions related to the digits of large numbers.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on floating‐point numeric tokens (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Shelter
    -0.07
     Aure
    -0.06
     Walnut
    -0.06
    /sn
    -0.06
     Chủ
    -0.06
    _TRI
    -0.06
    	func
    -0.06
    징
    -0.06
     σύ
    -0.06
    -Sep
    -0.06
    POSITIVE LOGITS
    (mapStateToProps
    0.07
    Χ
    0.07
    currentPage
    0.07
     momentos
    0.07
     acceso
    0.06
    OrCreate
    0.06
     compensated
    0.06
    assessment
    0.06
    imag
    0.06
    $(".
    0.06
    Act Density 0.003%

    No Known Activations