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

    Neuronpedia

    INDEX
    Explanations

    sections of code related to comments or documentation

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

    code comments and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.60
     GenerationType
    -0.59
    הערות
    -0.59
    +#+#
    -0.58
     للاسماء
    -0.57
    UrlResolution
    -0.56
     estekak
    -0.56
     Paglinawan
    -0.56
     تعدى
    -0.54
     ostavi
    -0.54
    POSITIVE LOGITS
    :✨
    0.53
    __(/*!
    0.49
    //
    0.42
     areas
    0.35
    ppelin
    0.35
    //
    0.34
     regions
    0.34
    Kariera
    0.34
     hora
    0.34
    <h2>
    0.33
    Act Density 0.010%

    No Known Activations