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

    Neuronpedia

    INDEX
    Explanations

    Proportion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     muted
    -0.07
    飞
    -0.07
     fö
    -0.07
     Differences
    -0.06
     sofas
    -0.06
    roles
    -0.06
     primera
    -0.06
     eliminar
    -0.06
     Vertex
    -0.06
     Spurs
    -0.06
    POSITIVE LOGITS
     Locke
    0.06
    [].
    0.06
     #[
    0.06
    启
    0.06
    patible
    0.06
    .tip
    0.06
    _IEnumerator
    0.06
    itol
    0.06
    ics
    0.06
     ilma
    0.06
    Act Density 0.018%

    No Known Activations