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

    Neuronpedia

    INDEX
    Explanations

    language labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    তে
    1.58
    ি
    1.57
    ut
    1.52
    да
    1.51
    zione
    1.51
    çı
    1.43
    ள்ளன
    1.41
    یم
    1.36
     Ս
    1.35
    َ
    1.34
    POSITIVE LOGITS
    震惊
    1.47
    ূত
    1.44
    不妨
    1.43
    解读
    1.40
    ன
    1.39
    nads
    1.35
    脸色
    1.34
    wards
    1.33
    简洁
    1.33
    นี่
    1.32
    Act Density 0.051%

    No Known Activations