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

    Neuronpedia

    INDEX
    Explanations

    terminology related to classification and grading systems

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

    class and grade classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wiktionnaire
    -0.44
     Familienname
    -0.42
    StoryboardSegue
    -0.40
    RenderAtEndOf
    -0.39
    Hauptartikel
    -0.39
    Gründe
    -0.39
     Spaß
    -0.39
    basicConfig
    -0.38
     ILLUSTRATIONS
    -0.37
     temprana
    -0.37
    POSITIVE LOGITS
     Grade
    0.70
     Class
    0.66
    grade
    0.64
    Grade
    0.63
    class
    0.62
     class
    0.62
     grade
    0.58
     autorytatywna
    0.58
     Klasse
    0.57
    Class
    0.56
    Act Density 0.124%

    No Known Activations