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

    Neuronpedia

    INDEX
    Explanations

    C-style code syntax

    np_max-act · gemini-2.0-flash

    The neuron activates on structured code documentation comment syntax (e.g. /** … */, /// <summary> …) rather than on ordinary code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Rom
    -0.06
    鱼
    -0.06
     Asp
    -0.06
    SEM
    -0.06
     Maple
    -0.06
     difficulty
    -0.06
     maple
    -0.06
     Cummings
    -0.06
     kinh
    -0.06
     Burke
    -0.05
    POSITIVE LOGITS
    انا
    0.07
    ographics
    0.07
    ="">↵
    0.06
    =("
    0.06
     Breaking
    0.06
     Installing
    0.06
    єш
    0.06
    reload
    0.06
    Adding
    0.06
    search
    0.06
    Act Density 0.013%

    No Known Activations