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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     secretary
    -0.07
    鲲
    -0.07
    enth
    -0.07
    Ah
    -0.07
    相关部门
    -0.06
    旋
    -0.06
    .nom
    -0.06
     notices
    -0.06
    _SECOND
    -0.06
     blew
    -0.06
    POSITIVE LOGITS
    嚣
    0.08
     Housing
    0.07
    城镇化
    0.07
    _remain
    0.07
    حماس
    0.07
     vỏ
    0.07
    景象
    0.07
    茧
    0.07
     �
    0.07
    Ҽ
    0.06
    Act Density 0.065%

    No Known Activations