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

    Neuronpedia

    INDEX
    Explanations

    article followed by topic introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的
    0.29
    의
    0.28
    ід
    0.27
    ీ
    0.27
    сій
    0.26
    يد
    0.25
    ской
    0.25
     grids
    0.25
     cites
    0.25
    과
    0.25
    POSITIVE LOGITS
    value
    0.28
    ON
    0.28
    macos
    0.27
     продолжа
    0.27
    class
    0.27
    src
    0.27
    OS
    0.27
    pointer
    0.26
    store
    0.26
    recipe
    0.25
    Act Density 1.352%

    No Known Activations