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

    Neuronpedia

    INDEX
    Explanations

    names of specific things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     majestic
    0.35
    がたくさん
    0.31
     ہے۔
    0.29
     cementing
    0.29
     impermeable
    0.29
     prolific
    0.29
     hilly
    0.28
     classico
    0.28
     extends
    0.28
     suburbs
    0.28
    POSITIVE LOGITS
     puis
    0.37
    úl
    0.35
    program
    0.33
     voire
    0.33
     थीं
    0.33
     ثم
    0.32
    PROGRAM
    0.31
     মুক্তিবাহিনীর
    0.31
     البرنامج
    0.31
    ຜ
    0.30
    Act Density 0.056%

    No Known Activations