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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of arrays or array‐like data structures (e.g. “array,” “arrays,” “ids,” “_desc,” “zip,” “length”) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     backlight
    -0.07
    Ready
    -0.07
    );"
    -0.06
     оці
    -0.06
     TIMEOUT
    -0.06
     Cable
    -0.06
    dtype
    -0.06
    CommandLine
    -0.06
    Vis
    -0.06
    Cog
    -0.06
    POSITIVE LOGITS
    матрива
    0.07
    regation
    0.07
    ضي
    0.07
     Camping
    0.06
    ПК
    0.06
    —and
    0.06
     области
    0.06
    тобы
    0.06
    люча
    0.06
    -support
    0.06
    Act Density 0.053%

    No Known Activations