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

    Neuronpedia

    INDEX
    Explanations

    prepositions of location or inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ியுடன்
    0.43
     നിന്ന്
    0.39
     কাছে
    0.39
    สำหรับการ
    0.38
     এখান
    0.37
    mtrl
    0.37
    عند
    0.36
    으로부터
    0.36
    നിന്ന്
    0.36
    ToList
    0.35
    POSITIVE LOGITS
     în
    1.66
    ใน
    1.42
     فى
    1.35
     katika
    1.35
     në
    1.34
     in
    1.27
     във
    1.27
     dalam
    1.24
    อยู่ใน
    1.21
     ใน
    1.15
    Act Density 0.032%

    No Known Activations