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

    Neuronpedia

    INDEX
    Explanations

    cavity

    np_max-act · gemini-2.0-flash

    The neuron activates on words naming resonant optical structures—e.g. cavities, resonators, and related feedback terminology.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     цієї
    -0.07
     thinker
    -0.06
    REAT
    -0.06
     Eventually
    -0.06
    UIImage
    -0.06
    Disp
    -0.06
     temporary
    -0.06
     juices
    -0.06
    ляют
    -0.06
     lief
    -0.06
    POSITIVE LOGITS
    /QĐ
    0.07
     spoilers
    0.06
    airo
    0.06
     particip
    0.06
    neys
    0.06
     landlord
    0.06
    ./
    0.06
     […]...↵
    0.06
    ellery
    0.06
    .',
    0.06
    Act Density 0.003%

    No Known Activations