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

    Neuronpedia

    INDEX
    Explanations

    developer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sync
    -0.07
    urate
    -0.07
    坥
    -0.07
     sách
    -0.06
    躺在床上
    -0.06
    dığımız
    -0.06
     Altın
    -0.06
     وا
    -0.06
    	So
    -0.06
    取决
    -0.06
    POSITIVE LOGITS
     resh
    0.07
    .Attach
    0.07
     offsets
    0.07
     being
    0.07
     Heritage
    0.06
    尉
    0.06
    Nr
    0.06
     الجمه
    0.06
     arena
    0.06
     fri
    0.06
    Act Density 0.001%

    No Known Activations