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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Quantum
    -0.07
    ương
    -0.07
    ่าง
    -0.07
    不论是
    -0.06
    .to
    -0.06
    쫑
    -0.06
    :]↵↵
    -0.06
     Springs
    -0.06
    逆转
    -0.06
    或者其他
    -0.06
    POSITIVE LOGITS
     Idle
    0.10
    DataTask
    0.08
    PHY
    0.07
    Idle
    0.07
    溢
    0.07
    _IDLE
    0.07
    ᄃ
    0.07
    סר
    0.07
     idle
    0.07
    删
    0.06
    Act Density 0.002%

    No Known Activations