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

    Neuronpedia

    INDEX
    Explanations

    Places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sony
    -0.07
    (signature
    -0.07
     exposed
    -0.06
     Sony
    -0.06
     Portland
    -0.06
    vido
    -0.06
    athlon
    -0.06
    ิกายน
    -0.06
    试
    -0.06
    ические
    -0.06
    POSITIVE LOGITS
     EDIT
    0.07
    unload
    0.06
    pesan
    0.06
    خي
    0.06
     고
    0.06
    بینی
    0.06
     сдел
    0.06
    .Reverse
    0.06
    manual
    0.06
     iteration
    0.06
    Act Density 0.184%

    No Known Activations