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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    This neuron detects the start of quoted words or phrases (quotation‐mark tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    elligence
    -0.07
     bait
    -0.07
    DELAY
    -0.06
    egis
    -0.06
    갈
    -0.06
    лег
    -0.06
    ofi
    -0.06
    CCI
    -0.06
     ابت
    -0.06
    ccount
    -0.06
    POSITIVE LOGITS
    "k
    0.07
     bem
    0.07
     respecting
    0.07
     todos
    0.06
     '[
    0.06
    ("/{
    0.06
    -z
    0.06
    .Graph
    0.06
     never
    0.06
    _parameter
    0.06
    Act Density 0.078%

    No Known Activations