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

    Neuronpedia

    INDEX
    Explanations

    previous states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     घेऊ
    0.35
    हरूको
    0.35
    ణు
    0.35
    𝙥
    0.35
    後に
    0.34
    に対し
    0.34
    рованных
    0.34
    将于
    0.34
     करु
    0.34
     ချ
    0.33
    POSITIVE LOGITS
     previous
    1.52
     предыду
    1.34
    previous
    1.32
    Previous
    1.26
    之前的
    1.24
     sebelumnya
    1.23
     Previous
    1.22
     tidligere
    1.20
    以前
    1.20
     previously
    1.18
    Act Density 0.260%

    No Known Activations