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

    Neuronpedia

    INDEX
    Explanations

    pale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ソン
    -0.08
    arsers
    -0.07
    ンフ
    -0.07
     hubby
    -0.07
    ороз
    -0.07
    erguson
    -0.07
    been
    -0.07
    ック
    -0.07
    enums
    -0.06
    アップ
    -0.06
    POSITIVE LOGITS
     pale
    0.19
     Pale
    0.15
    Pale
    0.11
    544
    0.07
    pace
    0.06
     Paleo
    0.06
    .']
    0.06
     пад
    0.06
    淡
    0.06
    ={[
    0.06
    Act Density 0.002%

    No Known Activations