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

    Neuronpedia

    INDEX
    Explanations

    graphs and plots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ัคร
    0.45
    ნი
    0.42
    NSDictionary
    0.40
    requests
    0.39
    หมด
    0.39
     चरित्र
    0.39
    compatibility
    0.38
     consiguió
    0.38
     newToken
    0.38
    getNext
    0.38
    POSITIVE LOGITS
     plotted
    1.40
     plotting
    1.23
     graph
    1.22
     plot
    1.16
     Plot
    1.14
     그래프
    1.12
     legend
    1.10
     curves
    1.09
     Graph
    1.09
     axes
    1.08
    Act Density 0.061%

    No Known Activations