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

    Neuronpedia

    INDEX
    Explanations

    sellers, electrons, Write, letter, financial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    比亚
    1.26
    雁
    1.23
     मशीन
    1.22
     выбира
    1.22
     chickpeas
    1.19
     NACA
    1.16
     ማድረግ
    1.14
     Choosing
    1.14
     earm
    1.13
     selectInput
    1.13
    POSITIVE LOGITS
    as
    1.33
    de
    1.11
    asının
    1.03
    𝙤
    1.02
    ing
    1.02
    ث
    1.01
    in
    0.99
    arında
    0.98
    ೆಂದು
    0.97
    ະ
    0.97
    Act Density 0.000%

    No Known Activations