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

    Neuronpedia

    INDEX
    Explanations

    government legislation and policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ValueError
    0.54
    材质
    0.54
    检测
    0.53
     operands
    0.53
    误差
    0.52
     显示
    0.52
     கதாபாத்திர
    0.50
    Methylsulfanyl
    0.49
     处理
    0.48
    游戏
    0.48
    POSITIVE LOGITS
     legislation
    0.89
     government
    0.84
     initiatives
    0.84
    政策
    0.84
    government
    0.82
    legislation
    0.82
    policy
    0.80
     policy
    0.78
     mandate
    0.78
    initiative
    0.78
    Act Density 0.112%

    No Known Activations