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

    Neuronpedia

    INDEX
    Explanations

    formal salutations and introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     עד
    0.54
    ಚ
    0.50
     ות
    0.49
     fizz
    0.47
    টিয়ে
    0.43
    վել
    0.42
    終わり
    0.42
     ცი
    0.42
    धिकारियों
    0.41
    কৃত
    0.41
    POSITIVE LOGITS
    chauff
    0.48
    hn
    0.47
    ilets
    0.46
    ag
    0.46
    huang
    0.44
    dé
    0.43
    ink
    0.42
    inins
    0.42
    ，“
    0.42
    ks
    0.41
    Act Density 0.001%

    No Known Activations