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

    Neuronpedia

    INDEX
    Explanations

    rhyming words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     generalization
    0.49
     menghilangkan
    0.43
     wallets
    0.42
     moda
    0.41
     YAML
    0.41
     imagens
    0.41
     prendas
    0.41
     perda
    0.40
     atual
    0.40
     padrão
    0.40
    POSITIVE LOGITS
     मरी
    0.48
    rı
    0.46
     देऊन
    0.45
     получите
    0.45
     thầy
    0.44
     Вы
    0.43
    द्या
    0.43
     са
    0.43
     пля
    0.43
     прекра
    0.42
    Act Density 0.003%

    No Known Activations