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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on uppercase letter sequences—i.e. acronyms, initialisms, and capitalized abbreviations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     مشارکت
    -0.07
     encoding
    -0.06
    _bill
    -0.06
    queue
    -0.06
     SYSTEM
    -0.06
    -frame
    -0.06
    (so
    -0.06
    อนท
    -0.06
    .angle
    -0.06
     hodnot
    -0.06
    POSITIVE LOGITS
     Auburn
    0.07
    "On
    0.07
    'ils
    0.07
    ισε
    0.06
     Tories
    0.06
    @
    0.06
     Ubisoft
    0.06
    .rmtree
    0.06
     тщ
    0.06
    	dc
    0.06
    Act Density 0.521%

    No Known Activations