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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hos
    -0.08
     hemisphere
    -0.08
     ਵਾਲ
    -0.07
     Livro
    -0.07
     livros
    -0.07
     خاطر
    -0.07
    Vietnam
    -0.07
     Hab
    -0.07
     વખતે
    -0.07
     predecessors
    -0.07
    POSITIVE LOGITS
     behave
    0.10
     behaves
    0.09
     initialized
    0.09
    被冻结
    0.09
     behaving
    0.09
     подвер
    0.08
     ഇനി
    0.08
     nearing
    0.08
    停止
    0.08
     deslig
    0.08
    Act Density 0.143%

    No Known Activations