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

    Neuronpedia

    INDEX
    Explanations

    dogs and dog-related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    1.09
    ו
    1.09
    to
    1.08
    سي
    1.05
    زين
    1.00
    زى
    0.98
    ين
    0.95
     geométricas
    0.95
    سى
    0.93
    트는
    0.93
    POSITIVE LOGITS
     canine
    1.38
     dog
    1.29
     собаки
    1.26
     соба
    1.25
     DOG
    1.22
     dogs
    1.18
     and
    1.13
    dog
    1.11
    dogs
    1.08
    犬
    1.08
    Act Density 0.024%

    No Known Activations