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

    Neuronpedia

    INDEX
    Explanations

    Robo-Advisor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    1.20
    ы
    1.13
    s
    1.12
    ill
    1.10
    <0x0D>
    1.05
    િંગ
    1.05
    ים
    1.02
    x
    1.00
     тяжё
    0.99
    ς
    0.98
    POSITIVE LOGITS
    on
    2.03
    as
    1.67
    to
    1.53
    リ
    1.46
    RO
    1.38
    ON
    1.38
    SA
    1.36
    is
    1.35
    SER
    1.31
    os
    1.30
    Act Density 0.000%

    No Known Activations