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

    Neuronpedia

    INDEX
    Explanations

    python imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    勫
    1.29
     château
    1.14
     numéro
    1.09
     conç
    1.07
    Cette
    1.05
     número
    1.03
     Dél
    1.02
     Tämä
    1.01
     Número
    1.00
     Ç
    1.00
    POSITIVE LOGITS
    util
    1.12
     base
    1.07
    base
    1.05
    org
    1.00
    module
    0.96
    utils
    0.94
    math
    0.93
    server
    0.85
    test
    0.85
    ையினர்
    0.85
    Act Density 0.007%

    No Known Activations