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

    Neuronpedia

    INDEX
    Explanations

    function definitions and their associated metadata in code documentation

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

    Code or license-related text

    np_acts-logits-general · gemini-2.0-flash

    numerical expressions and legal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.78
    <eos>
    -0.67
    ↵↵↵
    -0.52
    ↵
    -0.49
    行政区划
    -0.48
    </strong>
    -0.44
    6
    -0.41
     oficiales
    -0.41
    </blockquote>
    -0.40
    ↵↵↵↵
    -0.40
    POSITIVE LOGITS
     Efq
    0.89
     وتسجيلات
    0.86
    ^(@)
    0.82
     InputDecoration
    0.80
     للاسماء
    0.77
     surla
    0.75
    ⓘ
    0.73
    ſelves
    0.72
    NewUrlParser
    0.71
     }}$}
    0.71
    Act Density 0.045%

    No Known Activations