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

    Neuronpedia

    INDEX
    Explanations

    landmark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     combine
    -0.84
    everywhere
    -0.83
     combined
    -0.79
     everywhere
    -0.75
    Everywhere
    -0.74
    TagMode
    -0.73
    Anywhere
    -0.72
     Combined
    -0.70
    combined
    -0.70
     väli
    -0.69
    POSITIVE LOGITS
    swatch
    0.71
    PageRoute
    0.67
    CustomAttributes
    0.67
    RectangleBorder
    0.66
    PageContext
    0.64
     acid
    0.61
     Oppen
    0.60
    sca
    0.59
    FragmentManager
    0.59
     aneurysm
    0.58
    Act Density 0.073%

    No Known Activations