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

    Neuronpedia

    INDEX
    Explanations

    warnings

    np_max-act · gemini-2.0-flash

    The neuron fires on references to Python’s warnings‐module functions and methods (e.g. filterwarnings, catch_warnings, simplefilter, resetwarnings), i.e. code that imports or calls the warnings API to suppress or manage warnings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    :"
    -0.07
    ");
↵
    -0.07
     tree
    -0.06
    bedo
    -0.06
    ↵↵↵↵↵↵↵
    -0.06
    -data
    -0.06
     Dispatcher
    -0.06
    ”.↵↵
    -0.06
    pod
    -0.06
    .↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
    \-
    0.07
     Innovative
    0.07
    fully
    0.06
    -ли
    0.06
     aggregated
    0.06
     آنلاین
    0.06
    _LINK
    0.06
    _EXPR
    0.06
     predominantly
    0.06
    95
    0.06
    Act Density 0.003%

    No Known Activations