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

    Neuronpedia

    INDEX
    Explanations

    Dungeons & Dragons

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of “Dungeons & Dragons” (and the “Dungeon & Dragons” tokens and ampersand) – i.e. references to the game’s name.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ferm
    -0.06
    Apparently
    -0.06
     مسائل
    -0.06
     tanker
    -0.06
    .nom
    -0.06
    berra
    -0.06
     км
    -0.05
    853
    -0.05
     Kardashian
    -0.05
    突然
    -0.05
    POSITIVE LOGITS
    /Q
    0.08
    ез
    0.07
    dehy
    0.07
    _mode
    0.07
     Await
    0.07
    's
    0.07
    +'</
    0.07
     published
    0.07
     Flyers
    0.07
     analytical
    0.07
    Act Density 0.008%

    No Known Activations