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

    Neuronpedia

    INDEX
    Explanations

    document structure elements or metadata, such as section titles and authorship information

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

    Copyright notices or attributions

    np_acts-logits-general · gemini-2.0-flash

    copyright notices and authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apimachinery
    -0.55
     sappiamo
    -0.48
     totiž
    -0.46
    TestingModule
    -0.45
    ViewFeatures
    -0.45
    WriteBarrier
    -0.43
    λικ
    -0.42
    <eos>
    -0.42
    stateParams
    -0.41
     étranger
    -0.41
    POSITIVE LOGITS
     <=",
    0.75
    tvguidetime
    0.75
     @}
    0.72
     kasarigan
    0.71
    MessageTagHelper
    0.70
    Viitteet
    0.69
    脚注の使い方
    0.67
     contributors
    0.67
    indelijk
    0.66
    RegressionTest
    0.65
    Act Density 0.292%

    No Known Activations