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

    Neuronpedia

    INDEX
    Explanations

    data analysis and feedback

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strenuous
    0.77
     vertu
    0.75
     sprinkled
    0.70
     accented
    0.69
     rejuvenated
    0.68
     устраи
    0.66
     στην
    0.65
     tasteful
    0.65
     tastefully
    0.65
     bohemian
    0.64
    POSITIVE LOGITS
     insights
    1.53
     data
    1.51
    分析
    1.47
    data
    1.45
     analyze
    1.41
    analyze
    1.40
     분석
    1.38
     analyse
    1.38
     analysis
    1.37
    Insights
    1.37
    Act Density 1.275%

    No Known Activations