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

    Neuronpedia

    INDEX
    Explanations

    Writing advice

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of the French word “personnage” (i.e. references to a (fictional) character).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Hits
    -0.07
    acam
    -0.07
     hit
    -0.07
     roy
    -0.06
    iversary
    -0.06
     Hosting
    -0.06
     caller
    -0.06
     Lux
    -0.06
     enabling
    -0.06
    endir
    -0.06
    POSITIVE LOGITS
     imageNamed
    0.06
    幸福
    0.06
    (:,:,
    0.06
    interopRequireDefault
    0.06
    @Module
    0.06
     heapq
    0.06
    hendis
    0.06
    考试
    0.06
    getSingleton
    0.06
    UINT
    0.06
    Act Density 0.050%

    No Known Activations