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

    Neuronpedia

    INDEX
    Explanations

    code block terminators and related syntax elements in programming

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

    parentheses and commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.74
     autorytatywna
    -0.69
    ագրություններ
    -0.64
     disambiguazione
    -0.62
    Autoritní
    -0.59
     clearColor
    -0.58
    MessageTagHelper
    -0.57
    MLLoader
    -0.57
    ineno
    -0.56
     الرياضيه
    -0.56
    POSITIVE LOGITS
    ↵↵↵
    0.85
    ↵↵↵↵
    0.85
    ↵↵↵↵↵↵↵
    0.80
    ↵↵↵↵↵↵
    0.77
    ↵↵↵↵↵
    0.73
    ↵↵↵↵↵↵↵↵↵↵
    0.71
    ↵↵↵↵↵↵↵↵
    0.70
    ↵↵↵↵↵↵↵↵↵
    0.70
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.68
    ↵↵↵↵↵↵↵↵↵↵↵
    0.66
    Act Density 0.011%

    No Known Activations