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

    Neuronpedia

    INDEX
    Explanations

    list items or bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     הת
    0.73
    ্থ
    0.72
     숨
    0.72
     bunlar
    0.72
    ಳಿತ
    0.71
    िकारक
    0.70
    ्रेडिट
    0.70
    ising
    0.67
    fds
    0.66
    f
    0.66
    POSITIVE LOGITS
    ‣
    0.86
    τερα
    0.83
    ⦁
    0.82
     principales
    0.82
    0.77
     வண்ண
    0.76
    āk
    0.75
    carousel
    0.75
    ادية
    0.75
    →
    0.75
    Act Density 0.631%

    No Known Activations