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

    Neuronpedia

    INDEX
    Explanations

    specific numerical formats and structural elements in the text

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

    dance and wheel and click

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cheminée
    -0.43
     Palabra
    -0.40
     épreuve
    -0.39
     dignité
    -0.39
    vezető
    -0.38
    Reprodução
    -0.37
     pauvreté
    -0.36
    ActiveRecord
    -0.36
    务
    -0.36
     réputation
    -0.35
    POSITIVE LOGITS
     estekak
    0.63
    ViewFeatures
    0.56
    hyrchwyd
    0.53
    SharedDtor
    0.50
    ftagPool
    0.50
     OMITBAD
    0.49
     يتيمه
    0.48
    irvana
    0.48
    ViewImports
    0.48
     utafitiHapana
    0.47
    Act Density 0.045%

    No Known Activations