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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    meal
    -0.07
    лев
    -0.07
     embarked
    -0.07
    踏入
    -0.07
    如今
    -0.07
    点燃
    -0.06
    iske
    -0.06
    dbh
    -0.06
     Cyber
    -0.06
       ↵    ↵
    -0.06
    POSITIVE LOGITS
    éric
    0.07
    reeting
    0.07
    ognition
    0.07
    meyeceği
    0.07
    增值
    0.07
     PostgreSQL
    0.06
    علامة
    0.06
    籁
    0.06
    _CAN
    0.06
     sentimental
    0.06
    Act Density 0.002%

    No Known Activations