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

    Neuronpedia

    INDEX
    Explanations

    dipole

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reign
    -0.08
     يلي
    -0.08
     יר
    -0.08
     Mud
    -0.08
    .Collectors
    -0.08
     kasama
    -0.08
     ruling
    -0.08
     المفت
    -0.08
     Angeboten
    -0.08
     ruled
    -0.07
    POSITIVE LOGITS
     antennas
    0.10
    -shaped
    0.09
    0.09
     tensors
    0.09
     antenna
    0.08
    -де
    0.08
    -sized
    0.08
    fold
    0.08
    -fold
    0.08
     embarrassment
    0.07
    Act Density 0.002%
    No Known Activations