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

    Neuronpedia

    INDEX
    Explanations

    references to popular food items and their cultural significance

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

    Preceding punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    food flavors and recipes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kháu
    -0.77
     ſta
    -0.68
    endela
    -0.65
     Efq
    -0.65
     ſa
    -0.64
    FunctionFlags
    -0.63
     diſt
    -0.63
     perſon
    -0.62
    ſelf
    -0.62
     poffe
    -0.62
    POSITIVE LOGITS
     tasted
    0.84
     delicious
    0.83
     flavorful
    0.82
     tastes
    0.80
     tasty
    0.79
    อร่อย
    0.74
     taste
    0.74
    🤤
    0.71
     recipe
    0.70
     savory
    0.70
    Act Density 0.276%

    No Known Activations