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

    Neuronpedia

    INDEX
    Explanations

    computer code/mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chaotic
    -0.07
     Kens
    -0.07
     Attribute
    -0.06
     conceal
    -0.06
     incub
    -0.06
    Reject
    -0.06
    counter
    -0.06
    >↵
    -0.06
    اح
    -0.06
    fixture
    -0.06
    POSITIVE LOGITS
     AssemblyTrademark
    0.07
    дан
    0.07
     모두
    0.07
     вже
    0.07
    监听页面
    0.06
     pem
    0.06
     hepsi
    0.06
     avg
    0.06
    Please
    0.06
     등록
    0.06
    Act Density 0.001%

    No Known Activations