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

    Neuronpedia

    INDEX
    Explanations

    references to lines in code or text

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

    line breaks and lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.53
    期刊论文
    -0.48
    ⓘ
    -0.45
     disponibilités
    -0.42
    LookAnd
    -0.42
     perdre
    -0.42
     yüzük
    -0.41
     vaut
    -0.40
     للمعارف
    -0.38
    يميديا
    -0.37
    POSITIVE LOGITS
     lines
    0.81
    Lines
    0.72
     line
    0.69
     newline
    0.67
    lines
    0.67
     Lines
    0.66
    addLine
    0.64
    Line
    0.60
    newLine
    0.60
    lineNumber
    0.59
    Act Density 0.030%

    No Known Activations