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

    Neuronpedia

    INDEX
    Explanations

    Okay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ਹੀ
    0.32
    SHE
    0.32
    是你
    0.32
     tripled
    0.30
    ढ़
    0.30
     Mushrooms
    0.30
    絕
    0.30
     খবর
    0.30
     fuse
    0.30
    বৃদ্ধি
    0.30
    POSITIVE LOGITS
     Schra
    0.34
     Buzz
    0.32
     Bei
    0.31
     Bü
    0.31
    Buzz
    0.31
     фло
    0.31
     Pickup
    0.29
     butler
    0.29
     Buz
    0.29
     However
    0.28
    Act Density 0.000%

    No Known Activations