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

    Neuronpedia

    INDEX
    Explanations

    device

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ListBox
    -0.07
    .map
    -0.06
    '<
    -0.06
     Susan
    -0.06
    Bar
    -0.06
     Menschen
    -0.06
    ，让
    -0.06
    Bill
    -0.06
    Counts
    -0.06
     Christians
    -0.06
    POSITIVE LOGITS
     onData
    0.07
    朝
    0.06
    _paragraph
    0.06
    เฉล
    0.06
    _typeDefinition
    0.06
     adip
    0.06
     pís
    0.06
     lenght
    0.06
    Dot
    0.06
    861
    0.06
    Act Density 0.041%

    No Known Activations