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

    Neuronpedia

    INDEX
    Explanations

    dates and years

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aisal
    0.37
    abbage
    0.32
     devra
    0.31
    c
    0.31
    unez
    0.30
    淍
    0.30
    తు
    0.29
     whim
    0.28
    auti
    0.28
    टका
    0.27
    POSITIVE LOGITS
     २०
    0.43
    revalidator
    0.35
    商标
    0.34
    话说
    0.33
     dignissimos
    0.32
     ۱۹
    0.32
    вості
    0.32
     amore
    0.31
    २०
    0.31
    mdash
    0.31
    Act Density 0.057%

    No Known Activations