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

    Neuronpedia

    INDEX
    Explanations

    code and file paths

    np_max-act · gemini-2.0-flash

    The neuron fires on programming identifiers (e.g. class, type, method, and control names in code), especially CamelCase or PascalCase tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Pep
    -0.07
     witnessing
    -0.07
    	service
    -0.07
     Marcel
    -0.07
     Gust
    -0.07
     uttered
    -0.06
     ninth
    -0.06
     Gard
    -0.06
     Glam
    -0.06
    _jwt
    -0.06
    POSITIVE LOGITS
    estyle
    0.07
    errat
    0.06
     payloads
    0.06
     Unknown
    0.06
     Resorts
    0.06
    ература
    0.06
    青年
    0.06
    _locals
    0.06
     Searching
    0.06
    References
    0.06
    Act Density 0.136%

    No Known Activations