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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alom
    -0.08
    מכבי
    -0.08
    修炼
    -0.07
    肌肤
    -0.07
    씌
    -0.07
    -tools
    -0.07
    ourg
    -0.07
    ani
    -0.07
    uppen
    -0.07
    uploads
    -0.07
    POSITIVE LOGITS
    餐饮
    0.07
     visitor
    0.07
     flight
    0.07
    .Live
    0.06
     ويم
    0.06
     rest
    0.06
     Click
    0.06
    .DrawString
    0.06
    ging
    0.06
     pizzas
    0.06
    Act Density 0.003%

    No Known Activations