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

    Neuronpedia

    INDEX
    Explanations

    classic basic pancakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     solle
    0.42
     Narrow
    0.41
     particuliers
    0.41
     Sat
    0.41
     Kyr
    0.39
     udało
    0.39
     tissus
    0.38
     आणखी
    0.38
    ”،
    0.38
     Unfortunately
    0.38
    POSITIVE LOGITS
    德国
    0.42
    美国的
    0.41
     मुद्रा
    0.39
     jabs
    0.38
    餐
    0.37
    لمانيا
    0.37
     점
    0.37
    美國
    0.36
    В
    0.36
     воск
    0.36
    Act Density 0.001%

    No Known Activations