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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "D
    -0.07
     emergency
    -0.07
     Grace
    -0.07
    strup
    -0.07
    emergency
    -0.06
    ěj
    -0.06
    _beam
    -0.06
     clazz
    -0.06
     township
    -0.06
     spou
    -0.06
    POSITIVE LOGITS
    ToolStripMenuItem
    0.07
    Calculate
    0.06
     збільш
    0.06
     LLVM
    0.06
     рекомендуется
    0.06
    ITableView
    0.06
     argues
    0.06
     Lux
    0.06
    <g
    0.06
    วรรณ
    0.06
    Act Density 0.001%

    No Known Activations