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

    Neuronpedia

    INDEX
    Explanations

    acted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leaks
    -0.07
    inine
    -0.07
     hi
    -0.07
    距離
    -0.07
     stray
    -0.06
     chờ
    -0.06
    控
    -0.06
    しまう
    -0.06
    。大
    -0.06
     Hyde
    -0.06
    POSITIVE LOGITS
    �
    0.06
     cuckold
    0.06
     هفته
    0.06
    ционный
    0.06
    optera
    0.06
     моя
    0.05
     большин
    0.05
    _gener
    0.05
     onFinish
    0.05
     Да
    0.05
    Act Density 0.230%

    No Known Activations