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

    Neuronpedia

    INDEX
    Explanations

    based analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elusive
    0.68
    uchos
    0.67
    newsletter
    0.65
    tellers
    0.64
    verick
    0.63
     ilg
    0.62
    ៅ
    0.60
     reassuring
    0.60
     पुष्टि
    0.58
     reassurance
    0.58
    POSITIVE LOGITS
     analysis
    1.57
     Analysis
    1.52
     analyse
    1.48
     análise
    1.48
     analyze
    1.48
     análisis
    1.48
     анализ
    1.48
    analysis
    1.47
     analý
    1.46
    Analysis
    1.42
    Act Density 0.649%

    No Known Activations