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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    感慨
    -0.07
     sağlamak
    -0.07
    ⻘
    -0.07
     nutzen
    -0.07
    _income
    -0.06
    .son
    -0.06
    ᕑ
    -0.06
    潔
    -0.06
    第一步
    -0.06
    虑
    -0.06
    POSITIVE LOGITS
     branded
    0.08
    Tensor
    0.08
     CRT
    0.07
     Borders
    0.07
    دان
    0.07
    Indented
    0.07
    引流
    0.07
     Progressive
    0.07
     Kubernetes
    0.07
     theological
    0.07
    Act Density 0.005%

    No Known Activations