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

    Neuronpedia

    INDEX
    Explanations

    as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ই
    1.50
    ।
    1.23
    !
    1.11
    ’
    1.07
    *
    1.04
    Ջ
    1.02
    ?
    1.00
    ﺐ
    0.99
    ”
    0.98
     그래서
    0.98
    POSITIVE LOGITS
    ামুটি
    1.45
    ut
    1.40
    ти
    1.30
    𓏧
    1.23
    一系列
    1.20
    ку
    1.18
    ቛ
    1.15
     intérieure
    1.14
    ্ী
    1.12
     ditambah
    1.12
    Act Density 0.031%

    No Known Activations