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

    Neuronpedia

    INDEX
    Explanations

    references to published works and academic discussions about them

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

    Editions, commentary, or introductions of books/films

    np_acts-logits-general · gemini-2.0-flash

    supplementary publication content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पत्र
    -0.46
     فنا
    -0.43
    ťaž
    -0.43
     capacité
    -0.42
     groupBox
    -0.41
    zám
    -0.41
    każ
    -0.40
     miệng
    -0.40
    styleable
    -0.40
    поро
    -0.39
    POSITIVE LOGITS
    ⓧ
    0.81
     annot
    0.75
     Савезне
    0.74
    はじめに
    0.74
     cherchés
    0.73
     Paglinawan
    0.72
    RegistryLite
    0.70
    enderror
    0.69
     annotated
    0.66
     ग्राहक
    0.66
    Act Density 0.249%

    No Known Activations