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

    Neuronpedia

    INDEX
    Explanations

    valuable insights and learned lessons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ತೋ
    0.79
     tampilan
    0.76
     imagines
    0.73
    affichage
    0.72
     extensions
    0.70
     uređ
    0.67
     그래프
    0.67
     coercion
    0.66
     belieb
    0.66
    ゾート
    0.66
    POSITIVE LOGITS
     lessons
    2.15
     Lessons
    2.08
     learnings
    2.03
    Lessons
    2.00
     valuable
    1.91
     insights
    1.90
    lessons
    1.89
     Valuable
    1.80
     lesson
    1.72
     Insights
    1.72
    Act Density 0.237%

    No Known Activations