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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     추
    -0.06
    (remove
    -0.06
    .Flush
    -0.06
    .Sqrt
    -0.06
    Ops
    -0.06
     Change
    -0.06
     Tips
    -0.06
    xbe
    -0.06
     अद
    -0.06
    .Tests
    -0.05
    POSITIVE LOGITS
    .inspect
    0.07
    .constant
    0.07
    日本
    0.07
     Chancellor
    0.07
     Bolivia
    0.07
     是
    0.06
     expecting
    0.06
     prone
    0.06
    pered
    0.06
     マ
    0.06
    Act Density 0.024%

    No Known Activations