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

    Neuronpedia

    INDEX
    Explanations

    dogs and cats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🏛
    0.55
    DBMS
    0.49
    ธุรก
    0.49
    WOM
    0.48
    whitespace
    0.48
    terrorism
    0.47
    权力
    0.47
     सिनेमा
    0.47
     piracy
    0.47
    政治
    0.46
    POSITIVE LOGITS
     dogs
    1.55
     canine
    1.41
     dog
    1.40
     pets
    1.28
     Dogs
    1.28
    Dogs
    1.27
    🐶
    1.26
     perros
    1.23
     собаки
    1.23
     Canine
    1.23
    Act Density 0.324%

    No Known Activations