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

    Neuronpedia

    INDEX
    Explanations

    lack of knowledge

    np_max-act · gemini-2.0-flash

    The neuron activates on question or inquiry phrases—particularly common question words (like “what,” “meaning,” etc.) in interrogative constructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .HandlerFunc
    -0.08
    _QUEUE
    -0.07
    ATTRIBUTE
    -0.07
     OnDestroy
    -0.06
    .GetAsync
    -0.06
     python
    -0.06
    python
    -0.06
    VectorXd
    -0.06
     multicast
    -0.06
     данны
    -0.06
    POSITIVE LOGITS
     stare
    0.07
     adverse
    0.07
     backstage
    0.07
    ์,
    0.07
    _tasks
    0.07
     give
    0.07
     undergo
    0.06
     NV
    0.06
    онов
    0.06
     $('
    0.06
    Act Density 0.028%

    No Known Activations