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

    Neuronpedia

    INDEX
    Explanations

    commands and guidelines related to community moderation and participation

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

    Moderation-related actions/roles (ban, moderator, edits)

    np_acts-logits-general · gemini-2.0-flash

    moderation and banning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.75
    舺
    -0.70
    ChildScrollView
    -0.60
    KommentareTeilen
    -0.59
    ValueStyle
    -0.58
     Biôgrafia
    -0.57
     juſ
    -0.56
     ::=
    -0.55
     telefónica
    -0.54
     aérea
    -0.54
    POSITIVE LOGITS
     moderation
    1.20
     moderators
    1.17
     moderator
    1.16
     Moder
    1.15
    moder
    1.09
     ban
    1.08
     banned
    1.08
     blocked
    1.07
     Moderator
    1.05
     mod
    1.05
    Act Density 0.471%

    No Known Activations