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

    Neuronpedia

    INDEX
    Explanations

    solutions and suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cookbook
    -0.07
    🌯
    -0.07
    .btnClose
    -0.07
     blasph
    -0.07
     notre
    -0.07
    复古
    -0.07
    wróci
    -0.07
     üstün
    -0.07
     ?>↵↵↵
    -0.07
    떪
    -0.07
    POSITIVE LOGITS
     pert
    0.08
    Distribution
    0.07
    _side
    0.07
    .Render
    0.07
    Country
    0.07
    歷
    0.07
    _LEVEL
    0.07
     Numbers
    0.07
    HAM
    0.07
    可控
    0.07
    Act Density 0.236%

    No Known Activations