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

    Neuronpedia

    INDEX
    Explanations

    words with multiple syllables that describe something's properties in a broad sense

    oai_token-act-pair · gemini-2.0-flash

    characteristics and properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.69
    DoubleQuotes
    -0.69
    LabelTagHelper
    -0.60
     astore
    -0.59
    ValueStyle
    -0.57
     AssemblyCulture
    -0.56
    TagMode
    -0.56
    nofollow
    -0.56
     trajets
    -0.56
    :✨
    -0.55
    POSITIVE LOGITS
     AttributeSet
    0.59
     nede
    0.49
    riwal
    0.49
     Akufo
    0.44
    ainville
    0.44
     MonoBehaviour
    0.42
     haus
    0.42
    testng
    0.41
     justi
    0.41
    IZONTAL
    0.41
    Act Density 1.094%

    No Known Activations