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

    Neuronpedia

    INDEX
    Explanations

    hearing native speakers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ouille
    1.16
    น
    1.14
     ordinary
    1.13
    mg
    1.11
    butene
    1.11
     ונ
    1.10
    ritte
    1.08
    polymer
    1.07
    âl
    1.04
    scalars
    1.04
    POSITIVE LOGITS
    ic
    1.48
    ع
    1.45
    o
    1.32
    ه
    1.26
    هي
    1.25
    oretically
    1.20
    ์
    1.17
    ⿴
    1.15
    这篇文章
    1.15
    인더
    1.14
    Act Density 0.000%

    No Known Activations