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

    Neuronpedia

    INDEX
    Explanations

    who is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ाई
    1.45
    客様
    1.45
     وهذه
    1.44
    ca
    1.41
     esist
    1.38
     socializing
    1.38
     대해
    1.37
    ﺐ
    1.37
    >−</
    1.36
    𝚐
    1.34
    POSITIVE LOGITS
    ل
    1.80
    न
    1.75
    ان
    1.70
    น
    1.70
    นี่
    1.61
    на
    1.47
    ן
    1.46
    л
    1.45
    त
    1.41
    ن
    1.39
    Act Density 0.065%

    No Known Activations