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

    Neuronpedia

    INDEX
    Explanations

    mentions of "palace" and variations of the word

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

    Palace, palaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ✭✭
    -0.55
     RN
    -0.47
     CBI
    -0.46
     RTE
    -0.46
    RN
    -0.46
     USN
    -0.44
     Crohn
    -0.44
     RIM
    -0.43
     firefighter
    -0.43
     Rn
    -0.42
    POSITIVE LOGITS
     Palace
    2.08
     palace
    2.00
    Palace
    1.97
    palace
    1.81
     palaces
    1.58
     palacio
    1.33
     palais
    1.16
     Palacio
    1.11
     Palacios
    1.03
    宫
    1.02
    Act Density 0.002%

    No Known Activations