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

    Neuronpedia

    INDEX
    Explanations

    as $

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ([],
    0.40
    FER
    0.40
     flank
    0.40
    רט
    0.40
    fcntl
    0.39
    etrotters
    0.39
    ólnie
    0.38
     cuest
    0.38
    Youth
    0.37
     különb
    0.37
    POSITIVE LOGITS
     единица
    0.42
     io
    0.41
     ху
    0.40
     лю
    0.38
     selenium
    0.38
     huy
    0.38
     Се
    0.37
    机器人
    0.37
    ✻
    0.37
     num
    0.36
    Act Density 0.001%

    No Known Activations