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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reserve
    -0.06
     gst
    -0.06
    *&
    -0.06
    $update
    -0.06
     Bên
    -0.06
    zier
    -0.06
     wrink
    -0.06
    _ed
    -0.06
    -legged
    -0.06
    .he
    -0.06
    POSITIVE LOGITS
    resh
    0.06
     مشکلات
    0.06
     такая
    0.06
    َس
    0.06
    Fresh
    0.06
    成本
    0.06
    etrofit
    0.06
    _OC
    0.06
     YYS
    0.06
     bütün
    0.06
    Act Density 0.081%

    No Known Activations