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

    Neuronpedia

    INDEX
    Explanations

    means

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >↵↵↵↵↵
    -0.07
    otel
    -0.07
     Tyler
    -0.07
    姐
    -0.06
     odor
    -0.06
    ett
    -0.06
     callers
    -0.06
     bott
    -0.06
     Carter
    -0.06
    .filters
    -0.06
    POSITIVE LOGITS
    货
    0.07
     هنگام
    0.07
    zman
    0.06
     Vas
    0.06
    晓
    0.06
     guarda
    0.06
    *time
    0.06
     través
    0.06
     Đối
    0.06
    貨
    0.06
    Act Density 0.005%

    No Known Activations