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

    Neuronpedia

    INDEX
    Explanations

    how data packets travel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vě
    1.35
     elucidate
    1.28
     irá
    1.24
     szö
    1.01
    ্র
    1.00
     dvě
    1.00
     summa
    1.00
     reverted
    0.97
     zwar
    0.96
     lig
    0.95
    POSITIVE LOGITS
    as
    1.38
    flow
    1.24
     Beste
    1.21
    isées
    1.19
    Repositories
    1.17
    asys
    1.15
     ribu
    1.10
    даги
    1.10
    asih
    1.08
    Crazy
    1.08
    Act Density 0.000%

    No Known Activations