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

    Neuronpedia

    INDEX
    Explanations

    Certificate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [r
    -0.07
    03
    -0.07
     EV
    -0.06
     saw
    -0.06
    Apps
    -0.06
    �
    -0.06
     flux
    -0.06
    [j
    -0.06
     headings
    -0.06
     pd
    -0.06
    POSITIVE LOGITS
     certificate
    0.15
     Certificate
    0.12
    certificate
    0.12
    Certificate
    0.12
     certificates
    0.12
    Certificates
    0.11
    ificates
    0.10
    cele
    0.08
    IFICATE
    0.08
    cate
    0.08
    Act Density 0.004%

    No Known Activations