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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "miracle."

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

    miracle or miraculous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heads
    -0.42
    ungs
    -0.41
     صفحۀ
    -0.39
    ings
    -0.38
    Woody
    -0.38
     Heads
    -0.38
     fleshy
    -0.38
    BY
    -0.38
     Pens
    -0.37
     Lath
    -0.37
    POSITIVE LOGITS
     Miracle
    2.19
     miracle
    2.16
    Miracle
    2.09
    miracle
    2.03
     miracles
    1.81
     Miracles
    1.73
     milagro
    1.46
     miraculous
    1.27
    奇迹
    1.21
     mira
    1.05
    Act Density 0.001%

    No Known Activations