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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their associated actions or events

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

    announcements and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rizona
    -0.37
    dikan
    -0.36
    orski
    -0.34
    penuhi
    -0.34
    )],
    -0.34
    심
    -0.33
     Bohn
    -0.33
     길
    -0.33
    orm
    -0.32
     그
    -0.32
    POSITIVE LOGITS
    Personendaten
    0.80
    awtextra
    0.73
    новништво
    0.70
    ImageContext
    0.66
    MLLoader
    0.64
    RegressionTest
    0.60
     ModelExpression
    0.60
    HtmlAttribute
    0.60
    QMetaType
    0.60
     AssemblyProduct
    0.59
    Act Density 0.192%

    No Known Activations