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

    Neuronpedia

    INDEX
    Explanations

    book in advance for popular activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Asia
    0.43
    アジア
    0.41
     immersion
    0.41
    വാസ
    0.41
     inclusivity
    0.41
    include
    0.40
    Asia
    0.40
    East
    0.38
    geoning
    0.38
    ylvan
    0.38
    POSITIVE LOGITS
     restaurantes
    0.69
     restaurants
    0.66
     taxis
    0.65
     restaurant
    0.64
     taxi
    0.63
     рестора
    0.61
     ресторан
    0.61
    Restaurants
    0.60
     музе
    0.60
     Restaurant
    0.59
    Act Density 0.004%

    No Known Activations