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

    Neuronpedia

    INDEX
    Explanations

    space and perception elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     في
    0.56
     توی
    0.56
     روی
    0.55
    บน
    0.55
     trên
    0.50
    ارك
    0.50
     ở
    0.47
     فى
    0.44
     در
    0.44
    في
    0.44
    POSITIVE LOGITS
    ที่มี
    0.42
    not
    0.40
     not
    0.40
     isopropyl
    0.39
    belum
    0.39
    ικ
    0.39
    ణి
    0.38
    ocyt
    0.38
    Allora
    0.38
    iedy
    0.37
    Act Density 0.066%

    No Known Activations