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

    Neuronpedia

    INDEX
    Explanations

    Radio and television programs

    np_max-act · gemini-2.0-flash

    The neuron activates on words describing creative‐performance actions and roles—like “perform,” “produce,” “create,” “starred”—and related nouns (e.g. “troupe,” “podcasts”) in an entertainment‐biography context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    comedians and their accomplishments in the entertainment industry.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .app
    -0.07
     aluminum
    -0.07
     Florida
    -0.07
     vibrations
    -0.07
    542
    -0.06
    yd
    -0.06
     Cambridge
    -0.06
    易
    -0.06
    ique
    -0.06
    inning
    -0.06
    POSITIVE LOGITS
    ('/:
    0.07
     alla
    0.07
    рогра
    0.06
    _insert
    0.06
    ้ด
    0.06
     toArray
    0.06
     IRC
    0.06
     acceso
    0.06
     OM
    0.06
    	URL
    0.06
    Act Density 0.022%

    No Known Activations