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

    Neuronpedia

    INDEX
    Explanations

    complex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    咊
    0.36
    忝
    0.35
     Whittier
    0.34
    ះ
    0.34
    ->_
    0.33
     lighter
    0.32
    更好地
    0.32
     ধ্যান
    0.32
     entusi
    0.32
    रिय
    0.32
    POSITIVE LOGITS
     complex
    4.31
    complex
    4.00
    Complex
    3.95
     Complex
    3.86
    复杂
    3.84
    複雑
    3.75
     komplex
    3.70
     COMPLEX
    3.70
     kompleks
    3.67
    複雜
    3.66
    Act Density 0.609%

    No Known Activations