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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and data manipulation in code snippets

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

    code identifiers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.63
     चीज़ों
    -0.59
     ModelExpression
    -0.59
     оригіналу
    -0.58
    AddTagHelper
    -0.55
     nahilalakip
    -0.54
    writerow
    -0.53
    RenderAtEndOf
    -0.53
    Geplaatst
    -0.52
    Hozzáférés
    -0.51
    POSITIVE LOGITS
    AlterField
    0.42
    offsetWidth
    0.31
    typename
    0.31
     municipales
    0.30
    giene
    0.30
     dziecię
    0.30
    cault
    0.29
     teflon
    0.29
     viol
    0.29
    ベーション
    0.29
    Act Density 0.025%

    No Known Activations