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

    Neuronpedia

    INDEX
    Explanations

    Domains and web apps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unchanged
    -0.08
    .Path
    -0.08
    렬
    -0.08
    돈
    -0.07
     challenging
    -0.07
    īgs
    -0.07
    Liter
    -0.07
     poss
    -0.07
    Genre
    -0.07
    Dependent
    -0.07
    POSITIVE LOGITS
     localhost
    0.13
    localhost
    0.12
     сервис
    0.11
     wordpress
    0.10
     www
    0.10
     hostname
    0.10
    .hostname
    0.10
    .amazonaws
    0.10
     сайта
    0.10
    _hostname
    0.10
    Act Density 0.015%

    No Known Activations