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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (digits, numbers, and numeric constants).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    AES
    -0.07
    _chain
    -0.06
     prices
    -0.06
     billionaires
    -0.06
     heads
    -0.06
     buz
    -0.06
    	cancel
    -0.06
     Soviet
    -0.06
    -м
    -0.06
    Prime
    -0.06
    POSITIVE LOGITS
     син
    0.07
    .lat
    0.07
     preseason
    0.07
    ')[
    0.07
    ieves
    0.06
     elkaar
    0.06
     лют
    0.06
    .lu
    0.06
    unexpected
    0.06
     SRC
    0.06
    Act Density 0.069%

    No Known Activations