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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    درس
    -0.07
    ミ
    -0.06
    _Line
    -0.06
     awhile
    -0.06
     dữ
    -0.06
    DAO
    -0.06
     masculinity
    -0.06
    ruž
    -0.06
     entirety
    -0.06
    Γ
    -0.06
    POSITIVE LOGITS
        ↵    ↵    ↵
    0.08
            ↵        ↵        ↵
    0.06
     xp
    0.06
    ướng
    0.06
    .dataTables
    0.06
     Still
    0.06
     号
    0.06
    164
    0.06
    Glyph
    0.06
        ↵    ↵    ↵    ↵
    0.06
    Act Density 0.021%

    No Known Activations