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 strongly activates on code‐style identifiers and keywords (e.g. function or method names, class/library names, and SQL keywords).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    CEL
    -0.07
    	md
    -0.06
    _DELTA
    -0.06
    translated
    -0.06
    оп
    -0.06
     ріш
    -0.06
     Editors
    -0.06
    odon
    -0.06
     antenn
    -0.06
    ует
    -0.06
    POSITIVE LOGITS
    [sub
    0.07
    ,function
    0.07
     bởi
    0.07
     giao
    0.07
     erotische
    0.07
    すべて
    0.07
    Hair
    0.06
     nerve
    0.06
    랍
    0.06
    ++)
↵
    0.06
    Act Density 0.046%

    No Known Activations