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

    Neuronpedia

    INDEX
    Explanations

    multi-lingual specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.34
    ات
    1.33
    n
    1.31
    it
    1.26
    ع
    1.24
    um
    1.21
    v
    1.21
    k
    1.16
    te
    1.11
    č
    1.10
    POSITIVE LOGITS
    ಿಣ
    1.19
    เรา
    1.16
    하여
    1.15
    이지만
    1.10
    จะ
    1.04
    েইলি
    1.04
    我们
    1.03
    疠
    1.02
    ﻥ
    1.02
    可以
    1.01
    Act Density 0.919%

    No Known Activations