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

    Neuronpedia

    INDEX
    Explanations

    OpenGL code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seems
    -0.08
     Д
    -0.07
     wake
    -0.06
     damned
    -0.06
    ﯚ
    -0.06
     walmart
    -0.06
    试管婴儿
    -0.06
    海淀
    -0.06
    ↵
↵
    -0.06
    .ObjectModel
    -0.06
    POSITIVE LOGITS
    _HOST
    0.07
     xi
    0.07
    (pc
    0.07
    نسب
    0.07
    ADB
    0.07
    Pin
    0.07
    边
    0.07
    Cash
    0.07
    _CTX
    0.06
    pi
    0.06
    Act Density 0.027%

    No Known Activations