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

    Neuronpedia

    INDEX
    Explanations

    references to recipes and cooking instructions

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

    recipe for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Holl
    -0.44
     Landau
    -0.42
     al
    -0.40
    ьаж
    -0.39
     long
    -0.37
     Holden
    -0.37
     All
    -0.35
     Al
    -0.35
     $
    -0.35
     Bur
    -0.35
    POSITIVE LOGITS
    Recipe
    2.03
    recipe
    1.91
     Recipe
    1.71
     recipe
    1.54
     RECIPE
    1.47
    recipes
    1.43
    RECIPE
    1.41
     Recipes
    1.38
    Recipes
    1.36
     recipes
    1.21
    Act Density 0.007%

    No Known Activations