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

    Neuronpedia

    INDEX
    Explanations

    charts and guides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     Dang
    -0.08
    _=
    -0.08
     libera
    -0.08
     Barça
    -0.08
     উদ্যোগ
    -0.08
    dang
    -0.08
     ehk
    -0.08
     nort
    -0.07
     সুযোগ
    -0.07
    POSITIVE LOGITS
     classifications
    0.11
    _TABLE
    0.11
     Table
    0.11
    对应
    0.11
     thresholds
    0.11
     મુજબ
    0.11
     табли
    0.11
    分类
    0.10
     अनुसार
    0.10
     lookup
    0.10
    Act Density 0.124%

    No Known Activations