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

    Neuronpedia

    INDEX
    Explanations

    process, learning, development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    com
    0.46
    ation
    0.45
     ভিত্তিক
    0.44
    bf
    0.43
    স্বাস্থ্য
    0.43
    politics
    0.42
     காலம்
    0.42
    net
    0.42
    bin
    0.42
    class
    0.41
    POSITIVE LOGITS
    過程
    0.55
     процессе
    0.54
    过程中
    0.52
    過程中
    0.51
     пыта
    0.50
     ሂደት
    0.49
    ленні
    0.48
     hinder
    0.47
     során
    0.47
     과정
    0.46
    Act Density 0.047%

    No Known Activations