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

    Neuronpedia

    INDEX
    Explanations

    politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bast
    -0.07
    ()).
    -0.06
    Bat
    -0.06
    emand
    -0.06
    ELY
    -0.06
    atitis
    -0.06
    -live
    -0.06
    July
    -0.06
    (operator
    -0.06
    丁
    -0.06
    POSITIVE LOGITS
    normalized
    0.06
    organic
    0.06
    ок
    0.06
     written
    0.05
     çevir
    0.05
    .Stop
    0.05
    빛
    0.05
    나요
    0.05
    sample
    0.05
    (statement
    0.05
    Act Density 0.030%

    No Known Activations