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

    Neuronpedia

    INDEX
    Explanations

    testing and simulation contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     නිසා
    0.48
    вов
    0.45
     lớ
    0.43
    anneled
    0.39
     लोकल
    0.39
    テク
    0.38
     stratégies
    0.38
    伊斯
    0.37
     estrategias
    0.37
     strategies
    0.37
    POSITIVE LOGITS
     simulated
    1.11
     simulate
    1.03
     simulating
    1.03
     laboratory
    1.02
     simulator
    1.02
     simulates
    1.00
     simulators
    1.00
    模拟
    0.98
    模擬
    0.95
     bench
    0.90
    Act Density 0.026%

    No Known Activations