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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate duality or conflicting desires

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

    icing on the cake

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.80
    AndEndTag
    -0.68
    TagHelper
    -0.68
    principalColumn
    -0.65
    makeConstraints
    -0.63
    webElementXpaths
    -0.62
    ScopeManager
    -0.62
     <>",
    -0.62
     Administrativna
    -0.60
    OrWhiteSpace
    -0.59
    POSITIVE LOGITS
     cake
    1.20
     pie
    1.04
    cake
    0.98
     Cake
    0.84
     CAKE
    0.78
    pie
    0.75
    Cake
    0.75
     cakes
    0.72
     gâteau
    0.72
     Pie
    0.68
    Act Density 0.018%

    No Known Activations