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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OGND
    -0.72
     Roskov
    -0.71
     kasarigan
    -0.70
    XmlEnum
    -0.70
    bootstrapcdn
    -0.66
    BeginContext
    -0.63
     tartalomajánló
    -0.62
    invokeLater
    -0.61
     Италијани
    -0.60
     propOrder
    -0.60
    POSITIVE LOGITS
     referrerpolicy
    0.48
    󠁢
    0.47
    *}[
    0.43
    Handlung
    0.43
    alt
    0.42
     web
    0.41
     ALE
    0.41
    ultado
    0.40
    ün
    0.40
    sudoku
    0.39
    Act Density 0.000%

    No Known Activations