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

    Neuronpedia

    INDEX
    Explanations

    Schedules and activities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ID
    -0.08
     engine
    -0.07
    ัฐบาล
    -0.07
    itere
    -0.07
    Ь
    -0.07
    YT
    -0.07
    GC
    -0.07
     eing
    -0.07
    ucle
    -0.06
    (DIR
    -0.06
    POSITIVE LOGITS
    /ay
    0.06
     Zack
    0.06
     удал
    0.06
     商
    0.06
    кості
    0.06
    풍
    0.06
    ✔
    0.06
    UserName
    0.05
    authors
    0.05
     textu
    0.05
    Act Density 0.078%

    No Known Activations