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

    Neuronpedia

    INDEX
    Explanations

    p

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discontinued
    -0.07
    дет
    -0.07
    Int
    -0.06
    followers
    -0.06
     Safety
    -0.06
     så
    -0.06
     creek
    -0.06
    (Qt
    -0.06
     murdered
    -0.06
     warning
    -0.06
    POSITIVE LOGITS
    5
    0.06
     queryInterface
    0.06
    خی
    0.06
    935
    0.06
    ５
    0.06
    ेल
    0.06
     Πά
    0.06
     виготов
    0.06
     Occupy
    0.06
    .");↵
    0.06
    Act Density 0.005%

    No Known Activations