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

    Neuronpedia

    INDEX
    Explanations

    government, protection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lassen
    -0.08
     فمن
    -0.08
     სწავლ
    -0.08
    くだ
    -0.08
     смотреть
    -0.08
     famili
    -0.08
    herent
    -0.08
     woj
    -0.08
     tho
    -0.08
     אישי
    -0.07
    POSITIVE LOGITS
     retali
    0.09
    ীতে
    0.08
    终于
    0.08
     verschijnt
    0.08
     receives
    0.08
     complained
    0.08
    74
    0.08
     succumb
    0.08
    数据显示
    0.08
     Blumen
    0.07
    Act Density 0.135%

    No Known Activations