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

    Neuronpedia

    INDEX
    Explanations

    sequences or patterns in programming code

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

    foreign or multilingual text snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.36
    spaceBetween
    -0.36
     ویکی‌پدی
    -0.35
    -0.33
    xrTableCell
    -0.33
    Pla
    -0.32
    }],
    -0.32
     wh
    -0.32
    writeHead
    -0.32
    gettime
    -0.31
    POSITIVE LOGITS
    BeginInit
    0.59
     mijne
    0.54
    oarece
    0.52
     TAMBÉM
    0.52
    :✨
    0.50
     zijne
    0.49
     preſent
    0.49
     poichè
    0.48
    middels
    0.48
    ffions
    0.48
    Act Density 0.009%

    No Known Activations