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

    Neuronpedia

    INDEX
    Explanations

    Software licenses

    np_max-act · gemini-2.0-flash

    The neuron fires on decimal numeric literals (floating‐point numbers) appearing in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _STAT
    -0.07
    ellen
    -0.07
     والس
    -0.06
    列
    -0.06
     river
    -0.06
     sweets
    -0.06
     робота
    -0.06
     cms
    -0.06
    Opens
    -0.06
    iosis
    -0.06
    POSITIVE LOGITS
     vùng
    0.06
    -chair
    0.06
     realities
    0.06
    lıkları
    0.06
    .Anchor
    0.06
    roi
    0.06
    /component
    0.06
    ึ่
    0.06
    дрес
    0.06
     Tone
    0.06
    Act Density 0.003%

    No Known Activations