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

    Neuronpedia

    INDEX
    Explanations

    security restrictions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GameOver
    -0.08
    難しい
    -0.08
    叻
    -0.07
    こういう
    -0.07
    全力打造
    -0.07
     laat
    -0.07
    🤡
    -0.07
    _last
    -0.07
     procedure
    -0.07
    庆祝
    -0.07
    POSITIVE LOGITS
    نصر
    0.07
     redistribution
    0.07
     lenses
    0.07
     imágenes
    0.06
     Filme
    0.06
     Volk
    0.06
    (es
    0.06
    移民
    0.06
     lining
    0.06
     intoler
    0.06
    Act Density 0.175%

    No Known Activations