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

    Neuronpedia

    INDEX
    Explanations

    Movies

    np_max-act · gemini-2.0-flash

    films that blend elements of psychological intrigue, crime, and complex character relationships.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron spikes on the content words of movie‐plot summary sentences—for example, the verbs and nouns describing what happens in a film’s synopsis.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     desi
    -0.08
    Requested
    -0.07
     Â
    -0.07
     Pruitt
    -0.06
    suggest
    -0.06
    とした
    -0.06
    处理
    -0.06
    ヘ
    -0.06
    	area
    -0.06
    xef
    -0.06
    POSITIVE LOGITS
    .Country
    0.07
     psychiatric
    0.07
     microtime
    0.06
    gunakan
    0.06
    ponce
    0.06
    ilmek
    0.06
     Yak
    0.06
     năng
    0.06
    ẵng
    0.06
    ienia
    0.06
    Act Density 0.081%

    No Known Activations