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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .*
    -0.07
    Inter
    -0.06
     omp
    -0.06
    jwt
    -0.06
     hứ
    -0.06
     hone
    -0.06
     đai
    -0.06
    took
    -0.06
    ntl
    -0.06
    acf
    -0.06
    POSITIVE LOGITS
    Explore
    0.07
     /*!↵
    0.06
    _pal
    0.06
    /ng
    0.05
     INCLUDE
    0.05
     avatar
    0.05
     %%↵
    0.05
    Culture
    0.05
    .getError
    0.05
    .Foundation
    0.05
    Act Density 0.394%

    No Known Activations