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

    Neuronpedia

    INDEX
    Explanations

    code imports and includes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这一点
    0.44
    这也
    0.44
    गुन
    0.43
    世界
    0.41
    ா
    0.41
    𝖺
    0.41
     मिलती
    0.40
     dexterity
    0.39
    𝗇
    0.39
     явно
    0.38
    POSITIVE LOGITS
     retro
    0.40
     পানিতে
    0.39
    CCCN
    0.37
     genealogical
    0.37
    裔
    0.36
    အတွင်း
    0.35
    ဖြစ်သည်။
    0.35
     dial
    0.34
     dig
    0.34
     وفر
    0.34
    Act Density 0.045%

    No Known Activations