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

    Neuronpedia

    INDEX
    Explanations

    dog breeds and characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    动物
    0.88
     mammal
    0.86
     animal
    0.85
    動物
    0.85
     animale
    0.84
    animal
    0.83
     Dogg
    0.82
     동물
    0.81
     動物
    0.79
     prokary
    0.79
    POSITIVE LOGITS
     bred
    1.71
     breeding
    1.56
     breeders
    1.52
     breed
    1.50
    bred
    1.45
     Breeding
    1.37
    breeding
    1.37
     breeder
    1.33
     Bred
    1.29
    Bre
    1.29
    Act Density 0.120%

    No Known Activations