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

    Neuronpedia

    INDEX
    Explanations

    specialized characters and formatting in text

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

    Text snippets, code snippets, and dates

    np_acts-logits-general · gemini-2.0-flash

    code and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.78
    Життєпис
    -0.60
    </h1>
    -0.59
     picioare
    -0.56
     Paglinawan
    -0.54
     ș
    -0.54
     religieuses
    -0.54
     acestei
    -0.53
     Genu
    -0.53
     viață
    -0.51
    POSITIVE LOGITS
     فريبيس
    0.80
     resourceCulture
    0.78
     â
    0.75
    ftagPool
    0.66
     …
    0.64
    TagMode
    0.64
    Â
    0.62
    â
    0.58
    ReusableCell
    0.58
     صوتيه
    0.58
    Act Density 0.778%

    No Known Activations