INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    73
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    food-related terms that highlight flavors, cuisines, and cooking

    New Auto-Interp
    Negative Logits
     Audiodateien
    -0.65
    Personendaten
    -0.55
    AccessorTable
    -0.54
     ویکی‌پدیای
    -0.54
     OMITBAD
    -0.52
     виправивши
    -0.50
     Ανακτήθηκε
    -0.49
     ProtoMessage
    -0.49
    sistors
    -0.48
     Référence
    -0.47
    POSITIVE LOGITS
     culinary
    0.56
     food
    0.47
    ValueStyle
    0.46
     Culinary
    0.46
     gastronom
    0.45
    food
    0.45
     cuisine
    0.45
     restaurants
    0.43
    Eat
    0.43
     meal
    0.42
    Act Density 0.002%

    No Known Activations