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

    Neuronpedia

    INDEX
    Explanations

    Anime/Manga

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sew
    -0.07
     Fif
    -0.07
    (begin
    -0.06
     majet
    -0.06
    .AllArgsConstructor
    -0.06
    Observ
    -0.06
    нося
    -0.06
    (folder
    -0.06
     prostitutes
    -0.06
    Employees
    -0.06
    POSITIVE LOGITS
     buna
    0.06
     Воз
    0.06
    arf
    0.06
    πε
    0.06
    ierte
    0.06
    edu
    0.06
     specialised
    0.06
    requ
    0.06
     compar
    0.06
    �试
    0.06
    Act Density 0.002%

    No Known Activations