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

    Neuronpedia

    INDEX
    Explanations

    SE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     partager
    -0.07
     schwar
    -0.07
    bruar
    -0.07
     eget
    -0.07
     Urdu
    -0.07
     تغییر
    -0.07
     pued
    -0.06
    еку
    -0.06
     blog
    -0.06
    引用
    -0.06
    POSITIVE LOGITS
    Cond
    0.07
     dbHelper
    0.06
     Fasc
    0.06
    emin
    0.06
     meticulously
    0.06
     Revenge
    0.06
    .fname
    0.06
     Hacker
    0.06
     Livingston
    0.06
     (~
    0.06
    Act Density 0.002%

    No Known Activations