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

    Neuronpedia

    INDEX
    Explanations

    the command

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.21
     با
    0.19
    læ
    0.19
     همچ
    0.19
     Aussi
    0.19
     therewith
    0.18
     appunto
    0.18
     disgruntled
    0.18
    kannt
    0.18
     encore
    0.18
    POSITIVE LOGITS
    P
    0.19
    𝐆
    0.19
    테
    0.18
    TE
    0.18
    ⤠
    0.18
    ﻌ
    0.17
    驒
    0.17
    ATE
    0.17
     परीक्षण
    0.17
    Nuevo
    0.17
    Act Density 9.370%

    No Known Activations