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

    Neuronpedia

    INDEX
    Explanations

    current context and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imparts
    1.27
     डिज़ाइन
    1.11
     себя
    1.10
    southeast
    1.05
     değ
    1.05
    SE
    1.05
    अगर
    1.04
     দিল্ল
    1.04
    Designed
    1.01
    ίναι
    1.01
    POSITIVE LOGITS
     ترمیم
    1.11
    cun
    1.11
     Tua
    1.09
    mud
    1.05
     Sai
    1.03
     ደ
    1.02
     devil
    1.02
     सलमान
    1.01
     Texans
    1.01
    𝑟
    1.00
    Act Density 0.000%

    No Known Activations