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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reput
    -0.07
     рожд
    -0.07
    不同程度
    -0.07
    OPER
    -0.07
    点击查看
    -0.07
    �
    -0.07
     nghỉ
    -0.06
    تغير
    -0.06
    冶炼
    -0.06
    餐桌
    -0.06
    POSITIVE LOGITS
     środków
    0.08
     seriously
    0.08
     entreprises
    0.08
     []↵↵↵
    0.07
    个项目
    0.07
     deals
    0.07
    ounty
    0.07
    —is
    0.07
    Stra
    0.07
     евро
    0.07
    Act Density 0.017%

    No Known Activations