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

    Neuronpedia

    INDEX
    Explanations

    Russian language texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mir
    -0.09
    boll
    -0.08
     Creo
    -0.08
    atores
    -0.08
     disreg
    -0.08
     diferents
    -0.08
     destruir
    -0.08
     marcador
    -0.08
    Nivel
    -0.08
    ベル
    -0.08
    POSITIVE LOGITS
     грамот
    0.11
     золот
    0.10
     прекрас
    0.10
     грам
    0.10
     муд
    0.10
     ю
    0.10
     elegant
    0.10
     любви
    0.10
     рассказ
    0.09
     محبت
    0.09
    Act Density 0.058%

    No Known Activations