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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash

    The neuron flags named examples—proper nouns, dates, numbers, and specific references to organizations or events.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _times
    -0.06
    evenodd
    -0.06
    ιος
    -0.06
    .ToolStripItem
    -0.06
     곳
    -0.06
    _partial
    -0.06
     rear
    -0.06
    client
    -0.06
    Worker
    -0.06
    tail
    -0.06
    POSITIVE LOGITS
     demonstrates
    0.07
     always
    0.07
     []↵↵
    0.07
     underestimated
    0.06
    Everybody
    0.06
    TEE
    0.06
     caracteres
    0.06
     everybody
    0.06
    持续
    0.06
     spécial
    0.06
    Act Density 0.069%

    No Known Activations