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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mundial
    -0.07
    _HOUR
    -0.07
     RedirectTo
    -0.06
     belts
    -0.06
     TestUtils
    -0.06
     рецепт
    -0.06
     Bulg
    -0.06
    ことが
    -0.06
    SDL
    -0.06
    /tags
    -0.06
    POSITIVE LOGITS
     stunt
    0.07
     sprav
    0.06
    priv
    0.06
    fal
    0.06
    ordin
    0.06
    ーカー
    0.06
     Steam
    0.06
    .We
    0.06
    .Authorization
    0.06
    ику
    0.06
    Act Density 0.012%

    No Known Activations