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

    Neuronpedia

    INDEX
    Explanations

    code and statistical data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lessons
    0.94
     Spark
    0.78
    ्रेंस
    0.75
     tungsten
    0.73
     ARK
    0.72
     wishes
    0.72
     Final
    0.72
    टके
    0.72
     Sophomore
    0.71
     Nuggets
    0.70
    POSITIVE LOGITS
     gory
    0.63
    斑
    0.58
    Ia
    0.58
     mood
    0.58
     guard
    0.58
     আগ্র
    0.58
     ながら
    0.57
     varn
    0.56
    oblastic
    0.56
    物語
    0.56
    Act Density 0.021%

    No Known Activations