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

    Neuronpedia

    INDEX
    Explanations

    CSS styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    い
    1.35
    ी
    1.29
    i
    1.23
    ,
    1.21
     tại
    1.15
    -
    1.14
     at
    1.10
    л
    1.05
    <0x80>
    1.03
    いが
    0.99
    POSITIVE LOGITS
    UB
    1.20
    ↵
    1.16
    ICK
    1.10
    ست
    1.07
    ફેદ
    1.05
    ুল
    1.04
    ల
    1.04
    AS
    1.00
    UT
    0.96
    ...*/
    0.95
    Act Density 0.010%

    No Known Activations