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

    Neuronpedia

    INDEX
    Explanations

    references to users and user-related functionality

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

    Follows the word "user"

    np_acts-logits-general · gemini-2.0-flash

    user search, group, behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -1.13
    IUrlHelper
    -1.05
     ویکی‌پدی
    -1.04
    tagHelperRunner
    -0.99
    RenderAtEndOf
    -0.96
    PerformLayout
    -0.92
    WebVitals
    -0.91
     Roskov
    -0.89
    #+#
    -0.88
     تضيفلها
    -0.86
    POSITIVE LOGITS
     who
    0.63
     friendly
    0.61
    defin
    0.54
     defined
    0.53
     finais
    0.53
    Defined
    0.52
    names
    0.51
    ˈ
    0.50
     USER
    0.50
    groups
    0.50
    Act Density 0.043%

    No Known Activations