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

    Neuronpedia

    INDEX
    Explanations

    header

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of source or header files—especially references to “header,” “file,” and “.h/.cpp” contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    重点
    -0.07
     종
    -0.07
    ุงเทพมหานคร
    -0.06
     дан
    -0.06
     Sanctuary
    -0.06
     belirli
    -0.06
     fading
    -0.06
     Zwe
    -0.06
    、『
    -0.06
     сфері
    -0.06
    POSITIVE LOGITS
    ragments
    0.07
    /crypto
    0.07
     evaluation
    0.06
    >B
    0.06
    webkit
    0.06
    =dict
    0.06
     brutally
    0.06
    菲
    0.06
    酸
    0.06
    ropical
    0.06
    Act Density 0.002%

    No Known Activations