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

    Neuronpedia

    INDEX
    Explanations

    modularity, maintainability, readability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     have
    0.49
     তবুও
    0.43
    商
    0.43
    お
    0.40
     CONN
    0.39
    由
    0.39
     will
    0.39
    গো
    0.39
    不到
    0.38
     onward
    0.38
    POSITIVE LOGITS
     интенсив
    0.49
    ге
    0.46
    близи
    0.46
     рядом
    0.45
    xcodep
    0.44
     месте
    0.41
    લિક
    0.41
    или
    0.41
    μοί
    0.40
     kiện
    0.39
    Act Density 0.006%

    No Known Activations