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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prosperity
    -0.08
    城市发展
    -0.07
     META
    -0.07
    профессионал
    -0.07
    充满了
    -0.07
     çocuğu
    -0.07
    在生活中
    -0.06
     '<%=
    -0.06
     mr
    -0.06
    仕事を
    -0.06
    POSITIVE LOGITS
    ABCDEFG
    0.07
    碍
    0.07
     risky
    0.07
    漶
    0.06
    igans
    0.06
    �
    0.06
     Quiet
    0.06
    EN
    0.06
    nice
    0.06
    屑
    0.06
    Act Density 0.006%

    No Known Activations