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

    Neuronpedia

    INDEX
    Explanations

    spreadsheet formulas

    np_max-act · gemini-2.0-flash

    This neuron fires on language describing Excel‐formula construction—terms for identifying cells, functions, and formula logic.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (Be
    -0.07
     Ihrem
    -0.07
    (theme
    -0.06
    AVED
    -0.06
    iciones
    -0.06
    ror
    -0.06
     اختصاص
    -0.06
    emos
    -0.06
    ived
    -0.06
    션
    -0.06
    POSITIVE LOGITS
    سبة
    0.06
     وكانت
    0.06
    	unsigned
    0.06
     spectators
    0.06
     одерж
    0.06
     Dual
    0.06
    	HANDLE
    0.06
    Asset
    0.06
    сторія
    0.06
                          ↵
    0.06
    Act Density 0.038%

    No Known Activations