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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    在这种
    -0.07
    trusted
    -0.07
     submitted
    -0.07
     nothing
    -0.07
     Cout
    -0.07
     blasph
    -0.07
     ys
    -0.07
     useless
    -0.07
                      ↵
    -0.07
    Next
    -0.07
    POSITIVE LOGITS
    鞳
    0.08
    寥
    0.07
    les
    0.07
    =$(
    0.07
     عدد
    0.07
    ᠆
    0.07
     السعودي
    0.07
    .Abstract
    0.06
    ﻂ
    0.06
    ڂ
    0.06
    Act Density 0.020%

    No Known Activations