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

    Neuronpedia

    INDEX
    Explanations

    code or service changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Watt
    0.46
     watt
    0.46
     monopol
    0.45
    Watt
    0.45
     subsid
    0.43
     saver
    0.42
    Count
    0.40
     adidas
    0.40
     Adolf
    0.40
     wanton
    0.39
    POSITIVE LOGITS
     ficou
    0.47
     নিয়েছে
    0.46
     últimas
    0.45
     OS
    0.45
     পাঠিয়ে
    0.44
     TECHNIQUES
    0.44
     নিয়েছে
    0.43
    सूचित
    0.43
    trimmed
    0.43
    РУ
    0.42
    Act Density 0.004%

    No Known Activations