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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    悄然
    -0.07
     само
    -0.07
    再多
    -0.07
     JpaRepository
    -0.07
    澧
    -0.07
     mehr
    -0.07
    manuel
    -0.07
     פשוט
    -0.07
     chcia
    -0.07
    ﹃
    -0.07
    POSITIVE LOGITS
     lengths
    0.07
    _embed
    0.07
    上班
    0.07
    隨時
    0.07
     Ref
    0.07
    _CLOCK
    0.07
    .per
    0.07
    refer
    0.06
    )";↵
    0.06
    订
    0.06
    Act Density 0.002%

    No Known Activations