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

    Neuronpedia

    INDEX
    Explanations

    legal case titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ؛
    -0.07
    pově
    -0.07
    hani
    -0.07
     ticket
    -0.07
    改变
    -0.07
    ypi
    -0.06
     coroutine
    -0.06
    Pay
    -0.06
    ा-
    -0.06
    uede
    -0.06
    POSITIVE LOGITS
     incarnation
    0.06
    леч
    0.06
     philosophers
    0.06
     galer
    0.06
     accessing
    0.06
    (common
    0.06
    elerik
    0.06
    mers
    0.06
     terrace
    0.06
     Ä
    0.06
    Act Density 0.005%

    No Known Activations