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

    Neuronpedia

    INDEX
    Explanations

    science and engineering concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .policy
    -0.07
     liar
    -0.07
    Uri
    -0.06
    olarity
    -0.06
    (enable
    -0.06
    GENER
    -0.06
    ,''
    -0.06
     max
    -0.06
     century
    -0.06
    .sy
    -0.06
    POSITIVE LOGITS
     Little
    0.07
    ก
    0.07
    Site
    0.06
     Bac
    0.06
    /Page
    0.06
    具体
    0.06
    Little
    0.06
     च
    0.06
     Ames
    0.06
    거래가
    0.06
    Act Density 0.093%

    No Known Activations