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

    Neuronpedia

    INDEX
    Explanations

    1 following list or count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    א
    1.05
    ను
    1.01
    ي
    0.97
    我們可以
    0.96
    های
    0.95
    你
    0.92
    ৪
    0.91
    ah
    0.90
    ف
    0.90
    azion
    0.89
    POSITIVE LOGITS
    st
    1.10
    ️⃣
    0.95
    씩
    0.88
    ずつ
    0.84
    UNG
    0.79
    เดียว
    0.77
     जुट
    0.75
    ship
    0.74
    つの
    0.74
     zodiac
    0.72
    Act Density 0.199%

    No Known Activations