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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     JD
    -0.07
     dojo
    -0.07
    ''
    -0.07
     hồi
    -0.07
    عبة
    -0.07
    DER
    -0.07
    ounded
    -0.06
    탐
    -0.06
    ดร
    -0.06
    стью
    -0.06
    POSITIVE LOGITS
    _female
    0.08
    ẅ
    0.08
    妗
    0.07
     Rome
    0.07
    农村
    0.07
     purchasers
    0.07
    Retention
    0.07
    .ImageLayout
    0.07
    .InvariantCulture
    0.06
    城乡居民
    0.06
    Act Density 0.068%

    No Known Activations