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

    Neuronpedia

    INDEX
    Explanations

    scores and rankings in competitive events

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

    runner names and positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     चीज़ों
    -0.33
    FR
    -0.32
     yür
    -0.32
     IERC
    -0.31
    aarrggbb
    -0.30
    etc
    -0.30
    评估
    -0.29
     FR
    -0.29
    active
    -0.28
    host
    -0.28
    POSITIVE LOGITS
    RegressionTest
    0.59
    utives
    0.57
    NUMX
    0.56
    AndEndTag
    0.55
    EditorBrowsable
    0.54
     חיצוניים
    0.53
    脚注の使い方
    0.53
     runners
    0.52
     serializers
    0.52
    MessageTagHelper
    0.51
    Act Density 0.027%

    No Known Activations