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

    Neuronpedia

    INDEX
    Explanations

    references to authors or contributors in a publication

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

    initials or letter codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.66
    BagLayout
    -0.66
    tanleria
    -0.54
    StackNavigator
    -0.52
    copg
    -0.52
     ffilmiau
    -0.52
    Encyklopedia
    -0.50
    AndEndTag
    -0.49
     CreateTagHelper
    -0.48
    хьтан
    -0.48
    POSITIVE LOGITS
     TJ
    0.45
     RJ
    0.38
     CJ
    0.38
    boldmath
    0.38
     JD
    0.35
     تضيفلها
    0.34
    TJ
    0.34
    EJ
    0.34
    CJ
    0.33
    フォーマンス
    0.33
    Act Density 0.077%

    No Known Activations