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

    Neuronpedia

    INDEX
    Explanations

    beginner or learning ease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disappeared
    0.62
    धानिक
    0.61
    AnalyzeAction
    0.61
     फड
    0.59
     fetchData
    0.58
     facts
    0.58
    istica
    0.58
    elfde
    0.58
    准确
    0.57
    働く
    0.57
    POSITIVE LOGITS
     beginner
    3.94
     beginners
    3.86
    beginner
    3.39
     Beginners
    3.37
     Beginner
    3.35
     novice
    3.34
     newbie
    3.32
     novices
    3.01
     newbies
    2.96
    初心者
    2.83
    Act Density 1.611%

    No Known Activations