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

    Neuronpedia

    INDEX
    Explanations

    references to libraries and Wikipedia collaborations

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

    Wikipedia categories and articles needing references

    np_acts-logits-general · gemini-2.0-flash

    Category:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #+#
    -0.80
    NameInMap
    -0.75
    +#+
    -0.74
    Identyfik
    -0.69
    UnusedPrivate
    -0.69
    DeleteBehavior
    -0.68
    GraphicsUnit
    -0.67
    Према
    -0.67
    TintMode
    -0.66
     ModelExpression
    -0.66
    POSITIVE LOGITS
     Wikipedia
    0.97
     article
    0.87
     Wiki
    0.85
     wiki
    0.80
     Template
    0.80
    wiki
    0.79
     articles
    0.79
     Wik
    0.76
     {{
    0.75
    wik
    0.75
    Act Density 0.531%

    No Known Activations