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

    Neuronpedia

    INDEX
    Explanations

    relational prepositions across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ס
    0.40
     प्रसि
    0.40
    चारिक
    0.39
    gdock
    0.39
     ڈھ
    0.36
    レ
    0.35
     cautiously
    0.35
     tén
    0.35
    ス
    0.35
     cravings
    0.35
    POSITIVE LOGITS
     بالنسبة
    0.82
     chez
    0.79
     bagi
    0.75
    日本では
    0.71
     لدى
    0.70
    สำหรับ
    0.69
     עבור
    0.67
     بالنسبه
    0.67
     ở
    0.66
    សម្រាប់
    0.66
    Act Density 0.120%

    No Known Activations