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

    Neuronpedia

    INDEX
    Explanations

    references to castles and significant historical structures

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

    "castle" or related terms

    np_acts-logits-general · gemini-2.0-flash

    castles and palaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uLocal
    -0.59
    __':
    -0.54
     Zeal
    -0.54
    reactivex
    -0.52
    __":
    -0.50
     transfieras
    -0.50
    rungsseite
    -0.50
    Eman
    -0.48
     Qantas
    -0.48
     Zola
    -0.48
    POSITIVE LOGITS
     castle
    1.41
     Castle
    1.35
     castles
    1.20
     fortress
    1.20
    Castle
    1.17
     CASTLE
    1.09
     Fortress
    1.07
     castillo
    1.04
     palace
    1.02
     Palace
    1.01
    Act Density 0.193%

    No Known Activations