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

    Neuronpedia

    INDEX
    Explanations

    asking questions about assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ZE
    0.34
     auctions
    0.33
     jihad
    0.33
     SPEAK
    0.33
     SUBS
    0.33
    णू
    0.32
     ಖರೀ
    0.32
     CONS
    0.32
     befri
    0.32
     incul
    0.32
    POSITIVE LOGITS
    问
    0.42
     Answer
    0.40
    质疑
    0.39
    andrew
    0.38
    Andrew
    0.38
    疑问
    0.37
    問
    0.37
     hỏi
    0.37
     問
    0.37
     написал
    0.36
    Act Density 0.001%

    No Known Activations