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

    Neuronpedia

    INDEX
    Explanations

    patterns of numerical or quantitative comparisons

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

    legal citations and parentheticals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.63
    SharedDtor
    -0.62
     nahilalakip
    -0.59
     SqlCommand
    -0.58
    ImageField
    -0.56
    webdriver
    -0.56
    addContainerGap
    -0.56
     Cô
    -0.54
     bluse
    -0.54
     toJson
    -0.53
    POSITIVE LOGITS
    　　
    1.41
     　　
    0.85
    　　《
    0.70
    　　“
    0.69
    　　【
    0.61
    　　……
    0.60
    　　(
    0.60
    。　　
    0.57
    <bos>
    0.57
    　　（
    0.48
    Act Density 0.020%

    No Known Activations