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

    Neuronpedia

    INDEX
    Explanations

    language translation and learning resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    بوب
    0.48
     evicted
    0.44
     eviction
    0.44
     rationally
    0.42
     refocus
    0.40
    猀
    0.40
    बेट
    0.39
     collectively
    0.39
     antitrust
    0.39
     pelvic
    0.38
    POSITIVE LOGITS
     translation
    1.66
     translations
    1.57
     Translation
    1.55
     language
    1.54
     translator
    1.54
    翻译
    1.52
     bilingual
    1.52
     Translations
    1.52
     Language
    1.51
     bahasa
    1.51
    Act Density 0.138%

    No Known Activations