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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tonic
    -0.07
    ሓ
    -0.07
     subdued
    -0.07
    ﻍ
    -0.07
    🌵
    -0.07
    syscall
    -0.07
    赂
    -0.06
    .datasets
    -0.06
    中毒
    -0.06
     cute
    -0.06
    POSITIVE LOGITS
     berk
    0.07
     Olymp
    0.07
    偶然
    0.07
     asthma
    0.07
     أنه
    0.07
     Bras
    0.06
    CKET
    0.06
    Employees
    0.06
     Mutex
    0.06
    在一旁
    0.06
    Act Density 0.124%

    No Known Activations