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

    Neuronpedia

    INDEX
    Explanations

    browsers and operating systems

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of browser and OS identifiers (e.g. “Firefox,” “Chrome,” “Windows,” “OS”) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     역
    -0.07
    	init
    -0.07
     Our
    -0.07
     Bomb
    -0.06
    alnız
    -0.06
    śnie
    -0.06
     کامپی
    -0.06
    ond
    -0.06
     diploma
    -0.06
    .setStroke
    -0.06
    POSITIVE LOGITS
    ?-
    0.07
    _dw
    0.06
    润
    0.06
     submitted
    0.06
    =\"
    0.06
     جع
    0.06
     dav
    0.06
     architecture
    0.06
     margins
    0.06
     appropriated
    0.06
    Act Density 0.011%

    No Known Activations