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

    Neuronpedia

    INDEX
    Explanations

    German sentences containing modal verbs, passive voice and the word "Brief"

    oai_token-act-pair · gemini-2.0-flash

    specific programming or technical terms

    np_token-act-pair-logits · gpt-4o-mini

    technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nothing
    -0.44
    ansi
    -0.44
     by
    -0.43
     niets
    -0.43
    defineProperty
    -0.42
     they
    -0.42
    He
    -0.40
     elles
    -0.39
    ttes
    -0.39
    I
    -0.38
    POSITIVE LOGITS
    GraphicsUnit
    0.78
     surla
    0.77
    PMailer
    0.76
     تضيفلها
    0.72
    ItemBackground
    0.70
    UnusedPrivate
    0.68
    setupUi
    0.68
    LookAnd
    0.67
    "}")
    0.67
    GMENT
    0.66
    Act Density 1.094%

    No Known Activations