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

    Neuronpedia

    INDEX
    Explanations

    Definitions and introductions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    عز
    -0.07
     З
    -0.07
    ้าง
    -0.07
     من
    -0.07
    scar
    -0.07
     accustomed
    -0.07
    mal
    -0.07
     Appearance
    -0.07
    ובה
    -0.07
    qus
    -0.07
    POSITIVE LOGITS
    Graph
    0.08
    网站地图
    0.08
    ᶠ
    0.07
    𫍽
    0.07
    ʽ
    0.07
    🌍
    0.07
    .ToolStripButton
    0.07
     EITHER
    0.07
    村落
    0.07
     hybrids
    0.07
    Act Density 0.156%

    No Known Activations