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

    Neuronpedia

    INDEX
    Explanations

    grammar and parts of speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    داف
    0.53
     oyo
    0.48
     incentiv
    0.47
     चहल
    0.47
     mercados
    0.47
     लोगो
    0.47
    FindingsResponse
    0.47
    रेज
    0.46
     पेशेवर
    0.46
     négoci
    0.46
    POSITIVE LOGITS
     grammatical
    0.62
     noun
    0.61
     adjectives
    0.61
     adverb
    0.59
     sentence
    0.57
     grammar
    0.57
     verbs
    0.57
     verb
    0.57
    语法
    0.55
     grammat
    0.55
    Act Density 0.216%

    No Known Activations