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

    Neuronpedia

    INDEX
    Explanations

    numbers containing 8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ()[
    0.43
     оре
    0.42
     ауди
    0.41
    निंग
    0.41
    [_
    0.39
    నే
    0.39
    (||
    0.38
    ార్థ
    0.38
    mL
    0.37
    renderer
    0.37
    POSITIVE LOGITS
     दरअसल
    0.46
     Sebagai
    0.39
     wanna
    0.39
     Engl
    0.38
    smtb
    0.38
     আচ্ছা
    0.38
     Yeah
    0.38
     Recently
    0.37
     سابقا
    0.37
    <0xE2>
    0.36
    Act Density 0.003%

    No Known Activations