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

    Neuronpedia

    INDEX
    Explanations

    hua, ning, wa, ro locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    1.48
    $
    1.05
    ர்
    1.04
    ي
    1.04
    м
    0.99
    лло
    0.98
    -【
    0.96
    ル
    0.96
    ()}
    0.95
    ллі
    0.95
    POSITIVE LOGITS
    কে
    1.18
    2
    1.10
    ğini
    1.02
    ä
    1.00
    ất
    0.95
    ﺍ
    0.95
    IT
    0.93
    y
    0.92
     revital
    0.90
    av
    0.88
    Act Density 0.000%

    No Known Activations