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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tyto
    -0.07
    NOTE
    -0.06
    арт
    -0.06
     термін
    -0.06
    Ã
    -0.06
     zum
    -0.06
     amt
    -0.06
     سبتمبر
    -0.06
    ैट
    -0.06
     Charter
    -0.06
    POSITIVE LOGITS
     just
    0.08
    ledged
    0.08
    Equipment
    0.07
    َق
    0.07
    Wh
    0.07
    来自
    0.07
    指
    0.07
    Strong
    0.07
     APPLE
    0.07
    Pas
    0.07
    Act Density 0.023%

    No Known Activations