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

    Neuronpedia

    INDEX
    Explanations

    scientific paper introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Thirty
    -0.07
    为什么
    -0.07
    레이
    -0.06
     Reyes
    -0.06
    tracker
    -0.06
    .xr
    -0.06
    歷
    -0.06
    ्ज
    -0.06
    .car
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     ورزش
    0.07
     Brazilian
    0.07
     dissatisfaction
    0.06
    Deserialize
    0.06
    �
    0.06
     suspicions
    0.06
    atisfaction
    0.06
     oluştur
    0.06
     Ginger
    0.06
     peoples
    0.06
    Act Density 0.002%

    No Known Activations