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

    Neuronpedia

    INDEX
    Explanations

    generated text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     출력
    -0.09
    呻
    -0.08
     industriais
    -0.08
     industriales
    -0.08
    plies
    -0.08
     Nuk
    -0.08
    _interfaces
    -0.08
     lyd
    -0.08
     industrial
    -0.08
    工业
    -0.08
    POSITIVE LOGITS
    爱情
    0.14
     románt
    0.12
     soulmate
    0.12
     romant
    0.12
     প্রেম
    0.12
    恋
    0.11
     ప్రేమ
    0.11
     célib
    0.11
     காத
    0.11
    深爱
    0.11
    Act Density 0.047%

    No Known Activations