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

    Neuronpedia

    INDEX
    Explanations

    explaining mathematical or scientific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    复杂的
    0.59
    complex
    0.48
     শিল্প
    0.47
     phức
    0.46
     Complex
    0.45
    Complex
    0.44
     COMPLEX
    0.44
     complex
    0.44
     आजकल
    0.44
     kompleks
    0.43
    POSITIVE LOGITS
     meaning
    0.92
     의미
    0.91
    の意味
    0.90
     meanings
    0.89
    含义
    0.89
     significato
    0.88
    Meaning
    0.83
     significado
    0.82
     interpreta
    0.82
     Meaning
    0.80
    Act Density 0.009%

    No Known Activations