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

    Neuronpedia

    INDEX
    Explanations

    facial expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Asian
    -0.08
     Chargers
    -0.07
     Oven
    -0.07
    ifi
    -0.07
     orderBy
    -0.06
    AAD
    -0.06
     neredeyse
    -0.06
    DEBUG
    -0.06
     sucked
    -0.06
     peppers
    -0.06
    POSITIVE LOGITS
     극
    0.07
     NASA
    0.07
    ObjectType
    0.06
    склад
    0.06
    ='<
    0.06
     realidad
    0.06
     sayf
    0.06
    marsh
    0.06
    การส
    0.06
     impair
    0.06
    Act Density 0.023%

    No Known Activations