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

    Neuronpedia

    INDEX
    Explanations

    hardware

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ocean
    0.73
    Ꭹ
    0.71
     Ocean
    0.71
    海洋
    0.70
    Ocean
    0.68
     OCEAN
    0.67
     الاطلاع
    0.66
     cuk
    0.65
     বঙ্গবন্ধ
    0.64
     Krug
    0.63
    POSITIVE LOGITS
     hardware
    3.25
    Hardware
    3.13
     Hardware
    3.06
    hardware
    2.98
    硬件
    2.75
     हार्ड
    1.94
     firmware
    1.89
     Firmware
    1.84
     аппарат
    1.77
    ハード
    1.63
    Act Density 0.476%

    No Known Activations