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

    Neuronpedia

    INDEX
    Explanations

    you'd better + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    هایی
    1.56
    ו
    1.51
    ⌀
    1.46
     '/',
    1.45
     impetus
    1.44
    эння
    1.44
    ールド
    1.38
    简体
    1.37
     Setup
    1.37
     Optimize
    1.36
    POSITIVE LOGITS
     поча
    1.44
    ările
    1.43
    Số
    1.40
     буду
    1.36
     Consequently
    1.33
     Согласно
    1.30
    тому
    1.30
    しゃ
    1.29
     znajdują
    1.29
     табы
    1.29
    Act Density 0.000%

    No Known Activations