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

    Neuronpedia

    INDEX
    Explanations

    programming iterables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    signUp
    2.17
    뺐
    2.13
    argc
    2.11
    2.10
    𝐸
    2.09
    日間
    2.08
     tagName
    2.08
    କ
    2.08
     CGRect
    2.07
    ректор
    2.05
    POSITIVE LOGITS
    ه
    2.63
    an
    2.47
    o
    2.09
    л
    2.07
    ভাবে
    2.02
    ite
    2.01
    ها
    1.98
    neq
    1.95
    ft
    1.95
    ו
    1.90
    Act Density 0.003%

    No Known Activations