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

    Neuronpedia

    INDEX
    Explanations

    multilingual capabilities and information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leche
    0.36
     Gemüse
    0.36
     prezzo
    0.36
     Unterricht
    0.34
     anak
    0.33
     usando
    0.33
     atacar
    0.33
     genus
    0.33
     lingua
    0.32
     yung
    0.32
    POSITIVE LOGITS
    ávání
    0.38
    启用
    0.37
     হইয়৷
    0.36
    ᱪ
    0.35
    ধ্য
    0.35
     কিংবা
    0.35
    猞
    0.34
    各种
    0.34
    িকাল
    0.34
    𝐶
    0.33
    Act Density 0.449%

    No Known Activations