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

    Neuronpedia

    INDEX
    Explanations

    From

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thesis
    -0.07
    Dire
    -0.07
     unwrap
    -0.07
    {↵↵↵
    -0.07
    '],↵↵
    -0.06
    ávě
    -0.06
     Hav
    -0.06
    Fant
    -0.06
    `
↵
    -0.06
     reacted
    -0.06
    POSITIVE LOGITS
    لوب
    0.07
     Alert
    0.07
     Baum
    0.07
     jamais
    0.06
     kostenlos
    0.06
    .subtitle
    0.06
     nutritious
    0.06
     geliş
    0.06
     Casc
    0.06
     juste
    0.06
    Act Density 0.000%

    No Known Activations