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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uyu
    -0.07
    Suite
    -0.06
    .Asset
    -0.06
    .Distance
    -0.06
    Amb
    -0.06
     Arm
    -0.06
    .types
    -0.06
    lients
    -0.06
    лятор
    -0.06
    층의
    -0.06
    POSITIVE LOGITS
     Dod
    0.07
    esser
    0.06
     خبر
    0.06
    urdy
    0.06
     sayıda
    0.06
     cá
    0.06
    lacak
    0.06
     ди
    0.06
     Detailed
    0.06
    크기
    0.06
    Act Density 0.003%

    No Known Activations