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

    Neuronpedia

    INDEX
    Explanations

    references to expected outputs, examples, and specifications for data structures

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

    text describes something as follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.45
     Wikiseite
    -0.40
     fédéral
    -0.38
     ddelweddau
    -0.37
    wpi
    -0.37
     Miß
    -0.35
     Grüsse
    -0.34
    genodigd
    -0.34
    GEBURTSDATUM
    -0.33
     ultimi
    -0.33
    POSITIVE LOGITS
    bootstrapcdn
    0.54
     Italijani
    0.50
    ViewFeatures
    0.49
     initComponents
    0.48
    stap
    0.47
    UnusedPrivate
    0.47
    CreateMap
    0.47
    IndentedString
    0.46
    QMetaType
    0.46
     conv
    0.46
    Act Density 0.334%

    No Known Activations