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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash

    references to health conditions and medical symptoms.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on numeric tokens with decimal points (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _NODES
    -0.08
     noses
    -0.07
    理
    -0.07
     Ön
    -0.06
     login
    -0.06
     Θε
    -0.06
    	node
    -0.06
    요
    -0.06
    BR
    -0.06
     symb
    -0.06
    POSITIVE LOGITS
    '{
    0.07
     +#+#+#+
    0.07
    (:
    0.06
     rightfully
    0.06
    phetamine
    0.06
    /l
    0.06
     الاع
    0.06
    自动
    0.06
     allerdings
    0.06
    .Drawable
    0.06
    Act Density 0.096%

    No Known Activations