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

    Neuronpedia

    INDEX
    Explanations

    random text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curs
    -0.07
     Zah
    -0.06
    .bad
    -0.06
    (components
    -0.06
    ّد
    -0.06
    .waitFor
    -0.06
     ذات
    -0.06
    ド
    -0.06
     configs
    -0.06
    .old
    -0.06
    POSITIVE LOGITS
     région
    0.07
     دانشگاه
    0.07
     @"\
    0.06
    (Boolean
    0.06
     Closet
    0.06
    .cloudflare
    0.06
     dlou
    0.06
    .EntityFrameworkCore
    0.06
    struction
    0.06
     Jab
    0.06
    Act Density 0.025%

    No Known Activations