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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic and Indic prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    у
    0.89
     Besonders
    0.88
     Особенно
    0.87
     ಅನ್ನು
    0.86
    ές
    0.86
    ויות
    0.83
    งาน
    0.83
     faç
    0.83
     Reun
    0.82
     privados
    0.81
    POSITIVE LOGITS
    ه
    1.36
    𝘀
    1.27
    𝐬
    1.17
    oretically
    1.16
    aarr
    1.15
    ERTY
    1.12
    𝗟
    1.11
    aid
    1.08
    𝚋
    1.07
    𝐜
    1.06
    Act Density 0.047%

    No Known Activations