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

    Neuronpedia

    INDEX
    Explanations

    low-fat dairy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ส์
    1.31
     যাইহোক
    1.16
     fyrir
    1.15
     wirkt
    1.13
     भरना
    1.09
     sunglasses
    1.09
     berpikir
    1.09
    cellaneous
    1.07
     покрытие
    1.07
     wartości
    1.07
    POSITIVE LOGITS
    ه
    1.07
    러
    1.05
    О
    1.05
    гас
    0.97
    ganos
    0.95
    вайте
    0.94
     igual
    0.94
    o
    0.93
    ediakan
    0.93
    s
    0.93
    Act Density 0.004%

    No Known Activations