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

    Neuronpedia

    INDEX
    Explanations

    skin absorption

    np_max-act · gemini-2.0-flash

    The neuron specifically activates on numeric tokens—particularly decimals or measurements—highlighting occurrences of precise numeric values in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ků
    -0.08
    .glide
    -0.07
     Penis
    -0.07
    otine
    -0.07
     Brno
    -0.07
     сті
    -0.07
     але
    -0.06
     kort
    -0.06
     seismic
    -0.06
    fen
    -0.06
    POSITIVE LOGITS
    .qual
    0.06
    _PRODUCTS
    0.06
     двох
    0.06
    (property
    0.06
    	Render
    0.06
    Political
    0.06
    (errorMessage
    0.06
    (ExpectedConditions
    0.06
    _parsed
    0.06
     lagi
    0.06
    Act Density 0.012%

    No Known Activations