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

    Neuronpedia

    INDEX
    Explanations

    cats and related queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    માં
    1.51
    (
    1.34
    ي
    1.21
    ر
    1.19
    ים
    1.16
    ,
    1.13
    ς
    1.10
    ין
    1.05
    ம்
    1.04
    いきます
    1.04
    POSITIVE LOGITS
    cat
    1.38
    for
    1.37
     cats
    1.20
     Cats
    1.20
    cats
    1.19
     for
    1.15
    Cats
    1.15
    list
    1.12
    login
    1.08
    link
    1.06
    Act Density 0.037%

    No Known Activations