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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Screen
    -0.08
    lenmiş
    -0.07
    .setCode
    -0.07
     Mood
    -0.07
    uzu
    -0.07
    Escape
    -0.07
    周围的
    -0.07
    ulta
    -0.07
     bụng
    -0.07
    .GetName
    -0.07
    POSITIVE LOGITS
    _layer
    0.07
     fir
    0.07
     �
    0.07
     kilograms
    0.07
     pl
    0.07
     infantry
    0.07
    ivial
    0.07
    网首页
    0.06
     explained
    0.06
    (Optional
    0.06
    Act Density 0.008%

    No Known Activations