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

    Neuronpedia

    INDEX
    Explanations

    professional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oats
    -0.07
    coeff
    -0.07
     scept
    -0.06
    783
    -0.06
    converter
    -0.06
    _PRE
    -0.06
     clever
    -0.06
     nutritional
    -0.06
    438
    -0.06
    .PER
    -0.06
    POSITIVE LOGITS
    断
    0.07
     거래
    0.07
    斷
    0.07
    ？
    0.06
    _aug
    0.06
    0.06
     profesional
    0.06
     Ngày
    0.06
     unchanged
    0.06
     เด
    0.06
    Act Density 0.013%

    No Known Activations