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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating features or specifications of products and experiments

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

    Code, experiments, and technical documentation

    np_acts-logits-general · gemini-2.0-flash

    technical documentation sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mediately
    -0.45
     Stationary
    -0.42
     stationary
    -0.40
     Invasion
    -0.40
     estekak
    -0.40
     umbilical
    -0.39
     benches
    -0.39
    ulit
    -0.38
    urbation
    -0.38
    理石
    -0.38
    POSITIVE LOGITS
    :✨
    0.74
    webElementXpaths
    0.59
    Personendaten
    0.58
    ViewFeatures
    0.57
    parsedMessage
    0.50
     récon
    0.50
     pinulongan
    0.47
     DbSet
    0.45
     disambiguazione
    0.45
    styleType
    0.45
    Act Density 0.012%

    No Known Activations