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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、マ
    -0.06
     факт
    -0.06
    /open
    -0.06
    价格
    -0.05
     '\\
    -0.05
     усіх
    -0.05
     часов
    -0.05
    ，但
    -0.05
     pak
    -0.05
     Волод
    -0.05
    POSITIVE LOGITS
     Teaching
    0.07
    vou
    0.07
     Dietary
    0.07
    ريف
    0.06
    avez
    0.06
    -too
    0.06
     advent
    0.06
    itional
    0.06
    ých
    0.06
    inary
    0.06
    Act Density 0.005%

    No Known Activations