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

    Neuronpedia

    INDEX
    Explanations

    believing it's true

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fundador
    0.55
    КС
    0.54
     testimonies
    0.53
    􀂾
    0.51
     фонда
    0.51
     exuber
    0.50
     напомина
    0.50
     fundament
    0.50
    наче
    0.50
     ком
    0.50
    POSITIVE LOGITS
    ことができる
    0.55
    いただけ
    0.49
    2
    0.48
    頁
    0.48
    ProductName
    0.46
    Transaksi
    0.46
    that
    0.46
    ịnh
    0.45
    ải
    0.45
    વામાં
    0.45
    Act Density 0.000%

    No Known Activations