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

    Neuronpedia

    INDEX
    Explanations

    integer division

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    These
    0.48
    config
    0.48
    This
    0.46
    Anyone
    0.46
    It
    0.46
    Oct
    0.44
    新たな
    0.43
    慮
    0.42
    Performance
    0.42
    Cont
    0.42
    POSITIVE LOGITS
     timeCounter
    0.55
     nachos
    0.52
     होई
    0.49
     메뉴
    0.48
     MENU
    0.47
     pizzas
    0.46
     efter
    0.46
     MenuView
    0.46
     maken
    0.46
     waffles
    0.46
    Act Density 0.004%

    No Known Activations