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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    不失
    -0.09
     Political
    -0.07
     getaway
    -0.07
     SQLAlchemy
    -0.07
     Transport
    -0.07
    .numpy
    -0.07
     inh
    -0.07
     Nice
    -0.07
    릇
    -0.06
     getType
    -0.06
    POSITIVE LOGITS
    年后
    0.07
    情绪
    0.07
     descend
    0.07
    aleb
    0.06
    ائل
    0.06
    B
    0.06
    errar
    0.06
    ocused
    0.06
     AUDIO
    0.06
     frauen
    0.06
    Act Density 0.046%

    No Known Activations