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

    Neuronpedia

    INDEX
    Explanations

    say "period"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AMA
    -0.07
    Inserted
    -0.07
     distraction
    -0.07
    eld
    -0.07
    -selector
    -0.07
     socioeconomic
    -0.07
     Ald
    -0.07
    ahan
    -0.07
    -thumb
    -0.07
     Bans
    -0.07
    POSITIVE LOGITS
    心理
    0.08
    _);↵
    0.08
    /
↵
↵
    0.07
    쥰
    0.07
    로그
    0.07
    --
↵
    0.07
               
↵
    0.07
    ==>
    0.07
    python
    0.07
    ��
    0.06
    Act Density 0.003%

    No Known Activations