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

    Neuronpedia

    INDEX
    Explanations

    .sample

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    сыр
    -0.09
     Rechn
    -0.09
    obel
    -0.08
    >↵//
    -0.08
     okre
    -0.08
     jabón
    -0.08
     Maschinen
    -0.08
     šal
    -0.08
     erkennen
    -0.08
     buttery
    -0.08
    POSITIVE LOGITS
     randomly
    0.12
     sampling
    0.11
     shuffled
    0.11
     Sampling
    0.11
     sampled
    0.10
    sampling
    0.10
    Sampling
    0.10
    .shuffle
    0.10
     shortlist
    0.10
     chọn
    0.10
    Act Density 0.004%

    No Known Activations