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

    Neuronpedia

    INDEX
    Explanations

    Edinburgh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .vs
    -0.08
    Nos
    -0.07
     Hud
    -0.07
    找了
    -0.07
    _CLASS
    -0.07
    讹
    -0.07
     עצמם
    -0.06
    濡
    -0.06
    受到了
    -0.06
     Whenever
    -0.06
    POSITIVE LOGITS
    cake
    0.07
     Assassin
    0.07
     sản
    0.07
     inquiry
    0.07
     посл
    0.07
    taire
    0.07
    (DIR
    0.07
    吝
    0.07
    alers
    0.07
     charter
    0.06
    Act Density 0.001%

    No Known Activations