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

    Neuronpedia

    INDEX
    Explanations

    Java code blocks that handle exceptions

    oai_token-act-pair · gemini-2.0-flash

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Référence
    -0.59
    <bos>
    -0.58
    TypedDataSet
    -0.52
     Paglinawan
    -0.51
    ReusableCell
    -0.51
     relâche
    -0.49
    cense
    -0.48
    blico
    -0.48
    сло
    -0.47
     sto
    -0.46
    POSITIVE LOGITS
     Taktlose
    0.70
    SBATCH
    0.68
    strategia
    0.61
     disambiguazione
    0.60
    цездатний
    0.57
    bibitem
    0.55
    APOLIS
    0.54
    esterday
    0.54
    ürtel
    0.53
    Bronnen
    0.52
    Act Density 0.048%

    No Known Activations