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

    Neuronpedia

    INDEX
    Explanations

    code questions and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Stephen
    -0.08
     Stephen
    -0.08
    财务
    -0.07
    queryString
    -0.07
    (JFrame
    -0.07
     Helen
    -0.06
     Smith
    -0.06
    섥
    -0.06
    /swagger
    -0.06
    ScreenState
    -0.06
    POSITIVE LOGITS
    保护
    0.07
     Suitable
    0.07
    提取
    0.07
    导弹
    0.07
    GST
    0.07
    عاد
    0.07
    ated
    0.06
    .HTML
    0.06
    改正
    0.06
    ﻫ
    0.06
    Act Density 0.196%

    No Known Activations