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

    Neuronpedia

    INDEX
    Explanations

    grammatical structure and parts of speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    开源
    0.50
    ými
    0.50
     müşteri
    0.47
     Kunden
    0.44
     arbitrage
    0.44
     familiale
    0.43
     maatau
    0.43
     confidentialité
    0.42
    ულია
    0.42
     solusi
    0.41
    POSITIVE LOGITS
     noun
    1.35
     nouns
    1.30
    noun
    1.02
    Noun
    1.02
    nouns
    0.99
     adjectives
    0.98
     grammat
    0.87
     adjective
    0.87
     predicate
    0.84
     clause
    0.82
    Act Density 0.183%

    No Known Activations