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

    Neuronpedia

    INDEX
    Explanations

    statistics, data

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
     totalitarian
    -0.07
    uitar
    -0.06
    ----------------------------------------------------------------------
    -0.06
    (In
    -0.06
    	fr
    -0.06
    feito
    -0.06
    Add
    -0.06
     yardımc
    -0.06
    _pi
    -0.06
    _path
    -0.06
    POSITIVE LOGITS
    路程
    0.07
    政府
    0.07
     Medina
    0.07
    工程机械
    0.07
    前三季度
    0.07
    チーム
    0.07
    体制
    0.07
    chts
    0.06
    ỉnh
    0.06
    攻克
    0.06
    Act Density 0.132%

    No Known Activations