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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    瘼
    -0.07
    _CLEAR
    -0.07
    ilik
    -0.06
     Luckily
    -0.06
    HAVE
    -0.06
     Grammy
    -0.06
    口水
    -0.06
    Buf
    -0.06
    временно
    -0.06
    .getB
    -0.06
    POSITIVE LOGITS
    Platforms
    0.07
     toplant
    0.07
    Worksheet
    0.07
    0.06
    Env
    0.06
    .context
    0.06
     pierws
    0.06
     certainly
    0.06
    甚至连
    0.06
    PointCloud
    0.06
    Act Density 0.013%

    No Known Activations