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

    Neuronpedia

    INDEX
    Explanations

    realistic ambition, data minimization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     会
    0.53
     Су
    0.52
     ICR
    0.52
     Тех
    0.51
     製造
    0.50
     Đoàn
    0.50
     Services
    0.49
     FPR
    0.48
    巳
    0.48
     FPGA
    0.48
    POSITIVE LOGITS
    im
    0.59
    an
    0.56
    ž
    0.54
    ier
    0.53
    ed
    0.52
    ма
    0.52
    a
    0.50
    een
    0.50
    omere
    0.50
    ay
    0.49
    Act Density 0.001%

    No Known Activations