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

    Neuronpedia

    INDEX
    Explanations

    Instructions and updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للد
    -0.07
     vu
    -0.07
     zwei
    -0.07
    .mean
    -0.06
     appearances
    -0.06
     confidence
    -0.06
     eing
    -0.06
     Sour
    -0.06
     bloss
    -0.06
     shifted
    -0.06
    POSITIVE LOGITS
     Ply
    0.06
     memberId
    0.06
    navbar
    0.06
     Від
    0.06
     عشق
    0.06
    їв
    0.06
    Iterator
    0.06
    なんだ
    0.06
    FilePath
    0.06
    fmt
    0.06
    Act Density 0.004%

    No Known Activations