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

    Neuronpedia

    INDEX
    Explanations

    matrix operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Planner
    0.45
     координат
    0.42
     सांसदों
    0.42
     triángulos
    0.41
     trigonometric
    0.41
     Correlation
    0.41
    PathOf
    0.41
     empêcher
    0.40
    Planner
    0.38
    🔱
    0.38
    POSITIVE LOGITS
     Matrix
    0.54
     matrix
    0.53
    Matrix
    0.52
     operations
    0.49
     Matrices
    0.49
     matrices
    0.48
     MATRIX
    0.48
    matrix
    0.47
    operations
    0.47
     operazioni
    0.46
    Act Density 0.005%

    No Known Activations