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

    Neuronpedia

    INDEX
    Explanations

    fixed or absolute positioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pozycji
    0.81
     position
    0.80
     Position
    0.77
     позиции
    0.73
     posizione
    0.69
     posición
    0.68
     positional
    0.67
     POSITION
    0.67
     पोजीशन
    0.67
     positions
    0.66
    POSITIVE LOGITS
    left
    0.64
     inset
    0.62
    inset
    0.62
     left
    0.58
    right
    0.52
    start
    0.48
    pointers
    0.48
    Left
    0.47
    pointer
    0.46
     start
    0.45
    Act Density 0.008%

    No Known Activations