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

    Neuronpedia

    INDEX
    Explanations

    references to specific food items, particularly fruits and vegetables

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

    vegetables and fruits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UpInside
    -0.48
    Tracce
    -0.48
    PrintStream
    -0.42
    ANTLR
    -0.39
     duele
    -0.39
    cèse
    -0.38
    chowa
    -0.38
     bp
    -0.38
    bitField
    -0.37
     polvere
    -0.37
    POSITIVE LOGITS
     vegetables
    1.55
     fruits
    1.41
     vegetable
    1.36
     Vegetables
    1.30
     fruit
    1.30
     veggies
    1.26
    Vegetables
    1.22
     Fruits
    1.21
     tomatoes
    1.18
     Vegetable
    1.16
    Act Density 0.220%

    No Known Activations