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

    Neuronpedia

    INDEX
    Explanations

    unit conversions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    谈
    -0.07
    浦
    -0.07
    已经
    -0.07
     awards
    -0.07
    Ten
    -0.07
     Lo
    -0.07
    .push
    -0.07
    排行榜
    -0.07
     msg
    -0.07
     granted
    -0.07
    POSITIVE LOGITS
     XYZ
    0.07
     Mazda
    0.07
     xấu
    0.07
     Cleaning
    0.07
    훅
    0.07
     nigeria
    0.07
     Charger
    0.07
     Twist
    0.06
     Cosmetic
    0.06
     carriage
    0.06
    Act Density 0.001%

    No Known Activations