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

    Neuronpedia

    INDEX
    Explanations

    past participles and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     выбрать
    0.55
    わない
    0.52
     cached
    0.50
    するか
    0.49
    たちは
    0.48
    たちの
    0.47
    தியம்
    0.47
    cached
    0.46
    適切な
    0.46
    एचओ
    0.46
    POSITIVE LOGITS
    μη
    0.48
    nestjs
    0.44
    脛
    0.43
    olds
    0.43
    xido
    0.43
    ẵn
    0.43
    1
    0.43
    ie
    0.42
     "
    0.41
    écl
    0.41
    Act Density 0.000%

    No Known Activations