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

    Neuronpedia

    INDEX
    Explanations

    real or simulated experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strongly
    0.46
     sufficiently
    0.45
     reliably
    0.45
     consistently
    0.44
     purely
    0.44
     Strongly
    0.44
     terrestre
    0.42
     repeatedly
    0.40
    ait
    0.40
    lal
    0.39
    POSITIVE LOGITS
     simulated
    0.94
     Simulated
    0.83
    模擬
    0.80
     mock
    0.78
    真实的
    0.77
    実際の
    0.71
     настоя
    0.68
    実際に
    0.68
     실제
    0.66
    模拟
    0.66
    Act Density 0.030%

    No Known Activations