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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated punctuation or formatting

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

    Timestamps in subtitles

    np_acts-logits-general · gemini-2.0-flash

    timestamps and subtitles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.88
    Portály
    -0.82
    脚注の使い方
    -0.80
    RunWith
    -0.76
    AntiForgeryToken
    -0.74
    yntaxException
    -0.74
    astéro
    -0.73
     propOrder
    -0.73
     CreateTagHelper
    -0.73
     الرياضيه
    -0.72
    POSITIVE LOGITS
    اریخ
    0.66
     насељу
    0.53
     Melayu
    0.53
    ileo
    0.47
     $(".
    0.47
     fapt
    0.46
    стон
    0.45
    pagnes
    0.45
     compé
    0.44
    $(".
    0.42
    Act Density 0.452%

    No Known Activations