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

    Neuronpedia

    INDEX
    Explanations

    references to Roman Catholicism

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

    "Roman" followed by religious or geographic words

    np_acts-logits-general · gemini-2.0-flash

    Roman Catholic, Romantics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.85
     propOrder
    -0.81
     ModelExpression
    -0.80
     Monfieur
    -0.79
    RenderAtEndOf
    -0.79
     myſelf
    -0.75
     reaſon
    -0.74
     Efq
    -0.74
     itſelf
    -0.73
     grasshopper
    -0.72
    POSITIVE LOGITS
     Roman
    1.00
    Roman
    0.89
     Rom
    0.86
     roman
    0.77
     ROM
    0.77
     ROMAN
    0.77
     rom
    0.76
    Rom
    0.75
    roman
    0.75
     Rome
    0.74
    Act Density 0.104%

    No Known Activations