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

    Neuronpedia

    INDEX
    Explanations

    borrowed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bor
    -0.64
     borrow
    -0.64
    Y
    -0.63
     borrowed
    -0.62
     coup
    -0.57
    borrow
    -0.54
     Bon
    -0.51
    wski
    -0.50
    awtextra
    -0.50
     Š
    -0.49
    POSITIVE LOGITS
    FunctionFlags
    0.72
    ContentAsync
    0.68
     Jefus
    0.65
     Shakspeare
    0.65
     Cæsar
    0.65
    HideFlags
    0.65
     CreateTagHelper
    0.64
     Hift
    0.62
    setVerticalGroup
    0.61
    ſelf
    0.60
    Act Density 1.492%

    No Known Activations