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

    Neuronpedia

    INDEX
    Explanations

    inclusions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    祖父
    -0.08
     million
    -0.08
     tray
    -0.07
     war
    -0.07
     המת
    -0.07
    처럼
    -0.07
     стран
    -0.07
    зем
    -0.07
     trovare
    -0.07
    allest
    -0.07
    POSITIVE LOGITS
    French
    0.08
    itated
    0.08
    _REFER
    0.07
    Agents
    0.07
     Doug
    0.07
    ন
    0.07
    沏
    0.07
     üstün
    0.07
    OrElse
    0.07
     yelling
    0.07
    Act Density 0.027%

    No Known Activations