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

    Neuronpedia

    INDEX
    Explanations

    structure and organization in written content

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

    words ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.56
    ьажоргаш
    -0.48
     noqa
    -0.48
    contentLoaded
    -0.46
    TagMode
    -0.44
    openConnection
    -0.43
    ंदीखरीदारी
    -0.43
    clearInterval
    -0.43
    исленность
    -0.42
    例文帳に追加
    -0.41
    POSITIVE LOGITS
     HFILL
    0.47
    addCriterion
    0.46
    BufferException
    0.44
     nahilalakip
    0.44
    featureID
    0.40
    Carriera
    0.40
    /**
    0.39
    InjectAttribute
    0.39
    balleur
    0.38
    素质
    0.38
    Act Density 0.068%

    No Known Activations