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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -0.63
     itſelf
    -0.63
     متعلقه
    -0.60
     Jefus
    -0.59
    ſelves
    -0.56
     leſs
    -0.55
    ſelf
    -0.52
     Monfieur
    -0.52
     Archiproducts
    -0.51
     himſelf
    -0.51
    POSITIVE LOGITS
     pinulongan
    0.73
     autorytatywna
    0.65
    aarrggbb
    0.62
    webElementXpaths
    0.60
    eqn
    0.58
     par
    0.57
    Viited
    0.56
     Contents
    0.53
     codes
    0.52
    вня
    0.52
    Act Density 0.008%

    No Known Activations