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

    Neuronpedia

    INDEX
    Explanations

    prepositions in foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     idag
    0.43
     ohne
    0.41
     باستخدام
    0.40
    તાઓ
    0.38
     అక్క
    0.38
    ív
    0.36
     länge
    0.35
    adoo
    0.35
    মানা
    0.35
     জোগ
    0.35
    POSITIVE LOGITS
     dalam
    1.77
     trong
    1.77
     katika
    1.55
    dalam
    1.51
    ใน
    1.48
     ใน
    1.43
     nella
    1.42
    Dalam
    1.41
     Dalam
    1.40
     във
    1.38
    Act Density 0.018%

    No Known Activations