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

    Neuronpedia

    INDEX
    Explanations

    helper verbs, dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yu
    -0.07
    劭
    -0.07
    翊
    -0.06
    준
    -0.06
    💰
    -0.06
     مليار
    -0.06
    呖
    -0.06
    вро
    -0.06
    廉
    -0.06
    募资
    -0.06
    POSITIVE LOGITS
    两次
    0.07
     sweeping
    0.07
    Chicago
    0.07
     membranes
    0.07
    >>
    0.07
    开了
    0.07
    !",
    0.07
     inspection
    0.07
     декаб
    0.07
    ]);
    0.07
    Act Density 0.157%

    No Known Activations