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

    Neuronpedia

    INDEX
    Explanations

    the word "bright" and words associated with darkness, colors or caves.

    oai_token-act-pair · gemini-2.0-flash

    bright

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.94
    1
    -0.60
    ↵
    -0.57
    ">
    -0.55
      
    -0.54
     complete
    -0.53
    {
    -0.52
     total
    -0.51
     {
    -0.51
    2
    -0.50
    POSITIVE LOGITS
    +#+#
    1.16
    RenderAtEndOf
    1.16
    DockStyle
    1.11
    endpush
    1.03
     виправивши
    1.02
    ंदीखरीदारी
    1.02
     المعيارى
    1.02
     resourceCulture
    1.01
     <>",
    0.99
     فريبيس
    0.98
    Act Density 1.262%

    No Known Activations