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

    Neuronpedia

    INDEX
    Explanations

    any intellectual task

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ibilités
    0.41
    袜
    0.39
    掾
    0.38
    igheter
    0.37
    扎
    0.37
    地震
    0.37
    像素
    0.36
     செ
    0.36
    ྪ
    0.36
    Camera
    0.35
    POSITIVE LOGITS
     learning
    0.50
     aprender
    0.44
    學習
    0.44
     learn
    0.44
     aprendizaje
    0.41
    learn
    0.40
     Learning
    0.39
     teach
    0.39
     aprendiz
    0.39
     lern
    0.38
    Act Density 0.002%

    No Known Activations