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

    Neuronpedia

    INDEX
    Explanations

    left direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ഓഫ
    0.40
     saturation
    0.40
    大数据
    0.39
    árl
    0.39
     സേ
    0.38
     तीव्रता
    0.37
    ᄎ
    0.37
     ټ
    0.37
     катего
    0.36
    ρές
    0.36
    POSITIVE LOGITS
     left
    1.28
     lefty
    1.27
     Left
    1.26
    Left
    1.22
     LEFT
    1.16
     왼
    1.13
     दाएं
    1.12
     左
    1.11
    左
    1.11
    left
    1.09
    Act Density 0.032%

    No Known Activations