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

    Neuronpedia

    INDEX
    Explanations

    Ready to begin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आवश्यकता
    0.43
     Frankly
    0.42
     جائزہ
    0.41
    powiedz
    0.41
    暫
    0.41
    暂
    0.40
    тите
    0.39
    粵
    0.39
    sche
    0.39
    အစိတ်အပိုင်း
    0.39
    POSITIVE LOGITS
     GO
    0.74
     Go
    0.67
     START
    0.65
     Ready
    0.62
     READY
    0.61
     ready
    0.61
    READY
    0.60
     go
    0.59
    GO
    0.59
     start
    0.58
    Act Density 0.051%

    No Known Activations