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

    Neuronpedia

    INDEX
    Explanations

    a followed by g or l

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    1.03
    ↵
    0.81
    ات
    0.77
    ل
    0.70
    मध्ये
    0.66
    ir
    0.65
    де
    0.64
    ام
    0.62
    is
    0.61
    ות
    0.60
    POSITIVE LOGITS
    ﺐ
    0.56
    к
    0.53
     a
    0.52
    ן
    0.50
    人
    0.49
     năng
    0.48
    ד
    0.48
    ুই
    0.47
    0.47
    ી
    0.46
    Act Density 1.887%

    No Known Activations