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

    Neuronpedia

    INDEX
    Explanations

    URLs or web addresses

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

    URLs, often starting with "www" or containing file extensions

    np_acts-logits-general · gemini-2.0-flash

    web links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.64
    DeleteBehavior
    -0.64
     defStyleAttr
    -0.58
    RenderAtEndOf
    -0.55
    ])){
    -0.55
    stry
    -0.54
    DrawerToggle
    -0.50
     Linkedin
    -0.50
    ialog
    -0.50
     dod
    -0.49
    POSITIVE LOGITS
    TagHelper
    0.61
    /***/
    0.56
    tagHelper
    0.49
    ophile
    0.47
    gangenheit
    0.47
    ásban
    0.46
    ByPrimaryKey
    0.46
     tin
    0.44
    addGap
    0.43
    شوف
    0.42
    Act Density 0.122%

    No Known Activations