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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric IDs

    np_max-act · gemini-2.0-flash

    The neuron fires on sequences of digits and hexadecimal‐style identifiers (GUIDs/request-IDs) embedded in HTTP headers or metadata.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ongsTo
    -0.06
    rosis
    -0.06
    yte
    -0.06
    underline
    -0.06
     miniature
    -0.06
    agascar
    -0.06
    ptom
    -0.06
     armour
    -0.06
    ilo
    -0.06
    Junior
    -0.06
    POSITIVE LOGITS
    kB
    0.06
    .scss
    0.06
     faire
    0.06
     collapses
    0.06
     مبار
    0.06
    (Product
    0.06
    gesch
    0.06
    structors
    0.06
    hz
    0.06
     kap
    0.06
    Act Density 0.012%

    No Known Activations