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

    Neuronpedia

    INDEX
    Explanations

    trading and transactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    are
    1.27
    ן
    1.02
    ના
    0.99
    ू
    0.99
    4
    0.96
    ρα
    0.94
    रे
    0.92
    માં
    0.92
    人
    0.88
    5
    0.88
    POSITIVE LOGITS
     on
    1.11
    υτό
    1.02
    al
    0.97
    ड
    0.96
    x
    0.93
    त
    0.93
     as
    0.89
    ت
    0.88
    Z
    0.87
    ફેદ
    0.86
    Act Density 0.077%

    No Known Activations