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

    Neuronpedia

    INDEX
    Explanations

    initiating explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     будете
    0.39
     दूंगा
    0.38
     తాను
    0.38
    ঘ্রই
    0.37
     idem
    0.36
     অধিকাংশই
    0.36
     involvement
    0.35
     अथवा
    0.35
     telah
    0.35
    ,/
    0.34
    POSITIVE LOGITS
     başlayalım
    0.59
    看看
    0.52
     봅시다
    0.52
    ましょう
    0.51
    來看一下
    0.51
     bakalım
    0.50
    看一下
    0.50
    来看看
    0.50
     ourselves
    0.49
    しましょう
    0.49
    Act Density 0.405%

    No Known Activations