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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -analysis
    -0.07
     sonst
    -0.07
    书记
    -0.07
    ğını
    -0.07
     türl
    -0.07
    Neither
    -0.07
    adapt
    -0.07
    تحرير
    -0.07
    rine
    -0.07
    �
    -0.06
    POSITIVE LOGITS
    过往
    0.07
     dues
    0.07
     coming
    0.07
    ह
    0.07
    얍
    0.07
    MainMenu
    0.07
    낼
    0.07
     biz
    0.07
    回家
    0.06
    탔
    0.06
    Act Density 0.027%

    No Known Activations