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

    Neuronpedia

    INDEX
    Explanations

    references to sections, chapters, and subsections of a document

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

    section, chapter, example references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.69
    IntoConstraints
    -0.60
    UnusedPrivate
    -0.59
    XmlAccessType
    -0.53
     فريبيس
    -0.52
    XmlAccessorType
    -0.51
    IBOutlet
    -0.51
    TagMode
    -0.49
    AndEndTag
    -0.49
    StackNavigator
    -0.47
    POSITIVE LOGITS
    atguigu
    0.41
    etCode
    0.35
    原文
    0.35
    MVH
    0.35
     textbook
    0.35
    Raquel
    0.35
    autique
    0.34
    apprentissage
    0.34
     Raquel
    0.33
    orghini
    0.33
    Act Density 0.344%

    No Known Activations