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

    Neuronpedia

    INDEX
    Explanations

    assign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     agre
    -0.08
     법
    -0.08
     Holland
    -0.07
    (Action
    -0.07
    半月
    -0.07
    KeyPress
    -0.07
     youtube
    -0.07
    钱财
    -0.07
     Roger
    -0.07
     sạn
    -0.07
    POSITIVE LOGITS
     assigned
    0.08
    ]\\
    0.06
     an
    0.06
     Ambassador
    0.06
    CHAN
    0.06
    >")
    0.06
    .Matchers
    0.06
    す
    0.06
    SCALE
    0.06
     assigning
    0.06
    Act Density 0.018%

    No Known Activations