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

    Neuronpedia

    INDEX
    Explanations

    geometric shapes and plots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    òria
    0.44
    🧁
    0.40
    ម៉
    0.40
    ⚜
    0.39
    педия
    0.39
     consiguió
    0.39
    ⏱
    0.39
    焲
    0.39
    🚛
    0.38
    produktion
    0.38
    POSITIVE LOGITS
     arrows
    0.81
     lines
    0.68
     line
    0.68
     arrow
    0.66
     circles
    0.66
     plotted
    0.66
     vertical
    0.65
     horizontal
    0.64
     plot
    0.62
     shaded
    0.62
    Act Density 0.129%

    No Known Activations