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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    elements related to graphical user interface (GUI) components in programming contexts.

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

    The neuron is detecting numeric literals (floating‐point constants) in the source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (adj
    -0.06
    memset
    -0.06
     shear
    -0.06
    (shift
    -0.06
     grapes
    -0.06
     chained
    -0.06
    ochastic
    -0.06
    ptions
    -0.06
     Hood
    -0.06
     plastics
    -0.06
    POSITIVE LOGITS
     encontrado
    0.07
    >X
    0.07
    Starting
    0.06
    	writel
    0.06
    otence
    0.06
    _quote
    0.06
     furnished
    0.06
    opor
    0.06
    ибли
    0.06
     utilizando
    0.06
    Act Density 0.048%

    No Known Activations