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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     increase
    -0.07
     floating
    -0.07
    (comp
    -0.07
    .goal
    -0.07
     multipart
    -0.06
     Liên
    -0.06
    โทร
    -0.06
     Keep
    -0.06
    -risk
    -0.06
     Joan
    -0.06
    POSITIVE LOGITS
     funkce
    0.06
     decency
    0.06
    erto
    0.06
    stellung
    0.06
     conventions
    0.06
    NodeId
    0.06
    Science
    0.06
     effortlessly
    0.06
    &D
    0.06
    الی
    0.06
    Act Density 0.018%

    No Known Activations