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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "this" and various forms of document-related syntax and symbols

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

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >{@
    -0.42
     Réponses
    -0.40
    -------------</
    -0.35
    ništvo
    -0.34
     pinulongan
    -0.32
     Vorsch
    -0.30
     fieldNum
    -0.29
     كومونز
    -0.29
    Jeografia
    -0.29
    évaluateur
    -0.28
    POSITIVE LOGITS
    <unused80>
    0.59
    <unused8>
    0.59
    <unused15>
    0.59
    <unused52>
    0.59
    <unused71>
    0.59
    <unused3>
    0.59
    <unused14>
    0.59
    <unused43>
    0.59
    InjectAttribute
    0.59
    <unused16>
    0.59
    Act Density 0.032%

    No Known Activations