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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arabic
    -0.07
     tai
    -0.07
     Convention
    -0.07
     counties
    -0.07
    _path
    -0.06
     salaries
    -0.06
     renewable
    -0.06
     Graphic
    -0.06
     eliminated
    -0.06
     bulletin
    -0.06
    POSITIVE LOGITS
    지막
    0.06
    /Desktop
    0.06
     offen
    0.06
     Discussions
    0.06
    659
    0.06
    .Models
    0.06
    ован
    0.06
    .ShowDialog
    0.06
    HG
    0.06
    <O
    0.06
    Act Density 0.140%

    No Known Activations