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

    Neuronpedia

    INDEX
    Explanations

    judgment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    々
    -0.07
    .setItems
    -0.07
    녕하세요
    -0.07
    .ar
    -0.07
    Fine
    -0.07
    ball
    -0.06
    urpose
    -0.06
    买
    -0.06
    Arrays
    -0.06
    θα
    -0.06
    POSITIVE LOGITS
    essa
    0.07
     Pact
    0.06
     Dave
    0.06
     Morton
    0.06
    ugg
    0.06
     Stopwatch
    0.06
     confirm
    0.05
     xứ
    0.05
     České
    0.05
     ds
    0.05
    Act Density 0.003%

    No Known Activations