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

    Neuronpedia

    INDEX
    Explanations

    code and numbers

    np_max-act · gemini-2.0-flash

    The neuron is effectively inactive and does not respond to any tokens—it detects nothing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    !==
    -0.07
     Americ
    -0.07
     Walnut
    -0.06
    %.
    -0.06
    ilet
    -0.06
    Channel
    -0.06
    Things
    -0.06
     relig
    -0.06
    ARS
    -0.06
    care
    -0.06
    POSITIVE LOGITS
    ificación
    0.07
    єм
    0.07
    theless
    0.06
     فرهنگ
    0.06
    ribbon
    0.06
    _fold
    0.06
     httpResponse
    0.06
    retim
    0.06
     державної
    0.06
     Sum
    0.06
    Act Density 0.028%

    No Known Activations