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

    Neuronpedia

    INDEX
    Explanations

    death and suffering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulner
    -0.07
     pcs
    -0.07
    nad
    -0.07
     amateurs
    -0.07
     Fortune
    -0.07
    Headers
    -0.07
    妥
    -0.07
     downloaded
    -0.07
    .org
    -0.07
     pale
    -0.06
    POSITIVE LOGITS
    مقار
    0.07
    Ô
    0.07
     devis
    0.07
    붇
    0.07
    컫
    0.07
     attest
    0.07
     lễ
    0.07
    干什么
    0.07
    -link
    0.07
     Dann
    0.07
    Act Density 0.044%

    No Known Activations