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

    Neuronpedia

    INDEX
    Explanations

    references to diagrams and their associated components or versions

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

    starting with "Di" and "di"

    np_acts-logits-general · gemini-2.0-flash

    words starting with "Di"

    np_acts-logits-general · gemini-2.5-flash-lite

    words beginning with the “di”/“Di” prefix, especially at the start of capitalized names or scientific/technical terms.

    oai_token-act-pair · gpt-5Triggered by @igorkuztech
    New Auto-Interp
    Negative Logits
    UserScript
    -0.82
    UnitTesting
    -0.70
    ImageContext
    -0.67
    Rujuakan
    -0.65
     CURIAM
    -0.64
    StructEnd
    -0.64
    CreateModel
    -0.62
     Wikimedijinoj
    -0.62
    Diwedd
    -0.62
    encodeWith
    -0.61
    POSITIVE LOGITS
     Dietz
    0.77
    Di
    0.75
     Di
    0.72
     DiCaprio
    0.65
    Dí
    0.62
     DIB
    0.61
     di
    0.61
     Diar
    0.60
     Diab
    0.58
     îng
    0.56
    Act Density 0.254%

    No Known Activations