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

    Neuronpedia

    INDEX
    Explanations

    style or format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uedata
    1.10
    aabb
    1.02
    ền
    1.00
    es
    0.99
    ம்
    0.99
    0.98
    știg
    0.97
     fro
    0.96
    𝗰
    0.96
    etty
    0.96
    POSITIVE LOGITS
    I
    1.24
     richtigen
    1.13
     وفي
    1.10
     kommen
    1.06
    0
    1.06
     Freunde
    1.05
     Tiere
    1.05
     каком
    1.05
    ﻝ
    1.03
     sonst
    1.01
    Act Density 0.112%

    No Known Activations