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

    Neuronpedia

    INDEX
    Explanations

    possessive 's' or 's' ending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’।
    0.38
    та
    0.37
    ’
    0.37
    ر
    0.37
    6
    0.37
    ா
    0.37
    ‌ها
    0.36
    ’;
    0.34
    ق
    0.33
    ।’
    0.33
    POSITIVE LOGITS
    ched
    0.27
    ﺐ
    0.25
     и
    0.22
    '
    0.22
     proprie
    0.22
    0.22
     decentral
    0.21
    ching
    0.20
     réellement
    0.20
    ongen
    0.20
    Act Density 0.116%

    No Known Activations