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

    Neuronpedia

    INDEX
    Explanations

    http header keys and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tailed
    0.89
     vacances
    0.79
     rebates
    0.78
    isometric
    0.74
     discount
    0.73
    mleri
    0.72
    discount
    0.71
     retailer
    0.71
     competitive
    0.71
     rebate
    0.71
    POSITIVE LOGITS
     Headers
    1.20
     Header
    1.16
    Headers
    1.10
     headers
    1.01
    Header
    0.98
    headers
    0.96
    HEADER
    0.94
     header
    0.94
     Content
    0.92
     CEA
    0.85
    Act Density 0.044%

    No Known Activations