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

    Neuronpedia

    INDEX
    Explanations

    matrix multiplication and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stargo
    0.43
    íguez
    0.42
    fifty
    0.41
    чём
    0.39
    ტის
    0.39
    orys
    0.38
     гостей
    0.38
    ಬೇಕ
    0.38
     dostęp
    0.38
     všet
    0.38
    POSITIVE LOGITS
    ddots
    0.57
     Matrix
    0.45
     matrix
    0.44
    自己
    0.44
    Matrix
    0.40
    矩阵
    0.40
    |
    0.39
     (
    0.39
     मैट्रिक्स
    0.39
    matrix
    0.39
    Act Density 0.026%

    No Known Activations