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

    Neuronpedia

    INDEX
    Explanations

    message

    np_max-act · gemini-2.0-flash

    This neuron detects references to Protocol Buffer “message” constructs (e.g. the word “message” and related boilerplate in generated .proto code).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .createComponent
    -0.07
    .prod
    -0.07
    ColumnType
    -0.06
    orraine
    -0.06
     noses
    -0.06
    ucchini
    -0.06
     crash
    -0.06
    ounds
    -0.06
    -test
    -0.06
    _Code
    -0.06
    POSITIVE LOGITS
    _SUITE
    0.07
    MONTH
    0.07
     स
    0.06
     اص
    0.06
     gchar
    0.06
    Ы
    0.06
    ))]
    0.06
    μμα
    0.06
     �
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations