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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    863
    -0.07
     Rubio
    -0.06
     glands
    -0.06
    862
    -0.06
     unlawful
    -0.06
     racism
    -0.06
     Hubbard
    -0.06
    ub
    -0.06
     داشتن
    -0.06
    ﻴ
    -0.06
    POSITIVE LOGITS
    shop
    0.07
     बड
    0.07
    /system
    0.07
     cocktails
    0.07
     ultra
    0.06
     great
    0.06
    огра
    0.06
     Cookie
    0.06
     <?
    0.06
    Executable
    0.06
    Act Density 0.219%

    No Known Activations