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

    Neuronpedia

    INDEX
    Explanations

    penal enquiries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ған
    0.45
    প্রিয়
    0.41
    Є
    0.40
    ментів
    0.40
    goto
    0.40
    fillRect
    0.39
    питы
    0.39
    琹
    0.39
    将在
    0.39
    LayoutStyle
    0.39
    POSITIVE LOGITS
     ඔබට
    0.47
     penal
    0.46
     analyse
    0.44
     gegen
    0.43
     decent
    0.42
     bureaucratic
    0.42
     enquiries
    0.42
     unamb
    0.41
     marginalised
    0.41
     Penal
    0.40
    Act Density 0.006%

    No Known Activations