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

    Neuronpedia

    INDEX
    Explanations

    complex followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    奻
    0.46
    ovar
    0.43
     snug
    0.41
    ke
    0.40
    änn
    0.40
     જો
    0.39
    riele
    0.39
    的关键
    0.39
     fáciles
    0.39
     কেমন
    0.38
    POSITIVE LOGITS
    Complex
    1.15
     complex
    1.14
     complexe
    1.11
     complicated
    1.09
     Complex
    1.06
    complex
    1.06
    复杂
    1.06
     phức
    1.06
     COMPLEX
    1.06
    複雑
    1.06
    Act Density 0.019%

    No Known Activations