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

    Neuronpedia

    INDEX
    Explanations

    food, eating, and hunger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pay
    0.92
    Fluid
    0.91
    Music
    0.90
    Marshall
    0.89
    icheskij
    0.88
    Build
    0.86
    有一个
    0.86
    Trim
    0.84
    Accepted
    0.82
    льзова
    0.81
    POSITIVE LOGITS
     delicacies
    1.73
     eaten
    1.73
     meals
    1.72
     makanan
    1.66
     food
    1.62
     restaurants
    1.60
    อาหาร
    1.58
     meal
    1.56
     eating
    1.50
     mors
    1.49
    Act Density 0.155%

    No Known Activations