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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sendMessage
    -0.08
    �
    -0.07
    Club
    -0.07
    旅游局
    -0.07
    Listening
    -0.07
     Regiment
    -0.07
    \web
    -0.06
    HWND
    -0.06
     telefon
    -0.06
    LayoutConstraint
    -0.06
    POSITIVE LOGITS
    丰厚
    0.07
    -wrap
    0.07
    高三
    0.07
     ад
    0.07
     *</
    0.07
    ");↵↵↵
    0.07
    0.07
     mỗi
    0.06
    ******
↵
    0.06
     merging
    0.06
    Act Density 0.023%

    No Known Activations