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

    Neuronpedia

    INDEX
    Explanations

    user story: "website" and "orders"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ist
    1.06
    क
    1.04
    기
    0.98
    t
    0.97
    ͠
    0.94
    एंगे
    0.91
    ️
    0.90
    ville
    0.89
    خ
    0.89
    fö
    0.88
    POSITIVE LOGITS
    าลัย
    1.20
     innumerable
    1.16
    criptions
    1.16
    РЕ
    1.15
     महत्वपूर्ण
    1.14
    本事
    1.12
    ****/
    1.11
     numerous
    1.10
    <unused1082>
    1.10
    leşt
    1.10
    Act Density 0.002%

    No Known Activations