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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash

    The neuron fires on code identifiers that are function or macro names—particularly the leading action verbs (e.g. set, clear, init, register, parse, eval) in definitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    programming-related settings and configurations in a coding environment.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     škola
    -0.07
    -ce
    -0.07
    �
    -0.07
    offers
    -0.06
    SelfPermission
    -0.06
    업체
    -0.06
     Geç
    -0.06
    روف
    -0.06
    -comm
    -0.06
    /browser
    -0.06
    POSITIVE LOGITS
    	canvas
    0.06
     dwell
    0.06
     Having
    0.06
     sparked
    0.06
    	static
    0.06
    	const
    0.06
     css
    0.06
     NEED
    0.06
     oui
    0.06
     ans
    0.05
    Act Density 0.037%

    No Known Activations