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

    Neuronpedia

    INDEX
    Explanations

    C

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens in nutrient‐facts lists, especially numeric values and names of vitamins/minerals (e.g. “Vitamin C 3.01,” “Vitamin B6 1.04,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Threads
    -0.06
    Mus
    -0.06
     creamy
    -0.06
    azer
    -0.06
    appers
    -0.06
     Stack
    -0.06
     Tor
    -0.06
     sounds
    -0.06
     destroyed
    -0.06
     pulled
    -0.06
    POSITIVE LOGITS
     ๆ
    0.07
     nodeList
    0.06
    (chart
    0.06
    Incomplete
    0.06
     NoSuchElementException
    0.06
    局
    0.06
    歐
    0.06
    ย
    0.06
    าส
    0.06
     saison
    0.06
    Act Density 0.001%

    No Known Activations