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

    Neuronpedia

    INDEX
    Explanations

    XML parsing structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ки
    1.55
    ו
    1.54
    ial
    1.50
    一个
    1.48
    ד
    1.47
    з
    1.46
    queryString
    1.45
    ى
    1.43
     име
    1.41
    צים
    1.40
    POSITIVE LOGITS
    ﻪ
    2.68
    𝖚
    2.04
    ﻴ
    2.02
    ی
    1.98
    ﻨ
    1.91
    𝘻
    1.89
    𝖘
    1.86
    تهم
    1.84
    ﻔ
    1.83
    ﺢ
    1.82
    Act Density 0.000%

    No Known Activations