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

    Neuronpedia

    INDEX
    Explanations

    double taxation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kid
    -0.08
    Funnels
    -0.08
     Boy
    -0.08
    极速
    -0.07
    Kid
    -0.07
    しております
    -0.07
     thrilling
    -0.07
     Surgeon
    -0.07
    タイ
    -0.07
     rushing
    -0.07
    POSITIVE LOGITS
     treaty
    0.09
     europe
    0.09
     Frankreich
    0.09
     countries
    0.09
     matla
    0.09
     bounced
    0.09
     recipro
    0.08
     peyi
    0.08
     arbitration
    0.08
     BES
    0.08
    Act Density 0.001%

    No Known Activations