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

    Neuronpedia

    INDEX
    Explanations

    commas and semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	as
    -0.07
     aspirations
    -0.07
    asal
    -0.06
     twenties
    -0.06
    _Options
    -0.06
    Panel
    -0.06
    書
    -0.06
    Cx
    -0.06
    포츠
    -0.06
    Strip
    -0.06
    POSITIVE LOGITS
    Allowed
    0.07
    cribing
    0.06
     differential
    0.06
     decidedly
    0.06
     Ihr
    0.06
    .AutoScale
    0.06
    ğinde
    0.06
     getUserId
    0.06
    ToolStrip
    0.06
     cavalry
    0.06
    Act Density 0.054%

    No Known Activations