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

    Neuronpedia

    INDEX
    Explanations

    disclaimer at the end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ية
    0.44
    리
    0.41
    耱
    0.41
     analý
    0.41
    >;
    0.41
     análisis
    0.40
    ளையும்
    0.40
    语义
    0.40
    ᱔
    0.40
    কালের
    0.40
    POSITIVE LOGITS
     derecho
    0.45
     institu
    0.44
     왼쪽
    0.44
     droit
    0.41
     left
    0.41
     right
    0.41
     tod
    0.40
     direito
    0.39
     왼
    0.39
     maybe
    0.39
    Act Density 0.024%

    No Known Activations