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

    Neuronpedia

    INDEX
    Explanations

    uchar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xz
    -0.06
     Vũ
    -0.06
    _Player
    -0.06
     Hiro
    -0.06
     hubs
    -0.06
     Have
    -0.06
     Usa
    -0.06
    ुरस
    -0.06
    emplace
    -0.06
    xfe
    -0.06
    POSITIVE LOGITS
    (square
    0.08
    (expected
    0.07
     rtn
    0.07
    (CONFIG
    0.07
     звіт
    0.06
    录
    0.06
    ?<
    0.06
     assistir
    0.06
    居
    0.06
    مد
    0.06
    Act Density 0.014%

    No Known Activations