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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash

    This neuron detects code identifiers in CamelCase (e.g. class and function names like TestGetCookieKey, ConvertDataFormat, ConvUtilsTest, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     asshole
    -0.08
     ServiceException
    -0.06
     Saturdays
    -0.06
     Gods
    -0.06
    ILD
    -0.06
     Routes
    -0.06
     pkg
    -0.06
     využí
    -0.06
    mind
    -0.06
     route
    -0.06
    POSITIVE LOGITS
    �
    0.06
    �
    0.06
     mop
    0.06
     <>↵
    0.06
    �
    0.06
    決
    0.06
    (rest
    0.06
    警察
    0.05
     cham
    0.05
    prepend
    0.05
    Act Density 0.032%

    No Known Activations