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

    Neuronpedia

    INDEX
    Explanations

    Code/technical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nable
    -0.52
     capitalized
    -0.47
    able
    -0.46
     in
    -0.42
     rider
    -0.40
    rider
    -0.40
    POST
    -0.40
     dispatch
    -0.39
     Rider
    -0.39
     of
    -0.38
    POSITIVE LOGITS
     Ause
    0.83
    AddTagHelper
    0.79
    wapV
    0.76
     ErrIntOverflow
    0.73
    webElementXpaths
    0.72
     estekak
    0.71
    extAlignment
    0.71
    醐
    0.70
     متعلقه
    0.69
    ⓘ
    0.68
    Act Density 1.616%

    No Known Activations