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

    Neuronpedia

    INDEX
    Explanations

    win

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (server
    -0.07
    TJ
    -0.06
    calculator
    -0.06
    HEME
    -0.06
     نیر
    -0.06
    ohana
    -0.06
     tension
    -0.06
    yh
    -0.06
     maz
    -0.06
     listens
    -0.06
    POSITIVE LOGITS
     Spieler
    0.07
    sterdam
    0.07
     laut
    0.07
     пів
    0.06
     IRC
    0.06
     فيلم
    0.06
    остью
    0.06
     inters
    0.06
     فريق
    0.06
    .rec
    0.06
    Act Density 0.018%

    No Known Activations