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

    Neuronpedia

    INDEX
    Explanations

    desire/want

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.81
     ddelweddau
    -0.72
     ModelExpression
    -0.71
    ArrowToggle
    -0.70
    StoryboardSegue
    -0.70
    UnitTesting
    -0.68
    RenderAtEndOf
    -0.68
     autorytatywna
    -0.66
    ::$_
    -0.66
     يتيمه
    -0.64
    POSITIVE LOGITS
     the
    0.52
     faster
    0.50
     zijn
    0.49
     his
    0.49
     schneller
    0.47
     greater
    0.47
     himself
    0.47
    ka
    0.46
     a
    0.45
     triumph
    0.45
    Act Density 0.002%

    No Known Activations