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

    Neuronpedia

    INDEX
    Explanations

    threats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ################################################################
    -0.07
    ゝ
    -0.07
    삯
    -0.07
     informações
    -0.07
    վ
    -0.07
    right
    -0.06
     advertisement
    -0.06
     DETAILS
    -0.06
    �
    -0.06
    촣
    -0.06
    POSITIVE LOGITS
    功能
    0.07
     Snapchat
    0.07
     genocide
    0.07
    目前
    0.07
    发展目标
    0.06
    闯
    0.06
     الانتخاب
    0.06
    .CommandType
    0.06
    能不能
    0.06
    퓼
    0.06
    Act Density 0.072%

    No Known Activations