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

    Neuronpedia

    INDEX
    Explanations

    deliver a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    2.69
    تها
    1.84
    го
    1.79
    tio
    1.77
    い
    1.77
    tedir
    1.74
    tä
    1.70
    tı
    1.70
    tte
    1.67
    n
    1.64
    POSITIVE LOGITS
    <0x80>
    2.08
    𝗘
    1.82
    ра
    1.66
    𝐄
    1.66
     inoxidable
    1.64
    𝖽
    1.62
     richiest
    1.55
    を中心に
    1.53
    ◘
    1.49
    𝑢
    1.49
    Act Density 0.135%

    No Known Activations