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

    Neuronpedia

    INDEX
    Explanations

    programming data structures and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    F
    0.24
    ian
    0.23
    q
    0.23
    atar
    0.22
    ۔
    0.22
    https
    0.22
    linkedin
    0.22
    Singapore
    0.22
    graphql
    0.21
    싶
    0.21
    POSITIVE LOGITS
    ла
    0.31
    та
    0.28
    ною
    0.26
     testamentary
    0.26
    as
    0.26
    ни
    0.26
    ны
    0.26
     podendo
    0.26
    า
    0.26
    ะ
    0.26
    Act Density 2.455%

    No Known Activations