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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating updates or new developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    further positive additions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Erlebnis
    -0.32
     Abenteuer
    -0.28
     че
    -0.24
     Kraus
    -0.22
     strane
    -0.22
     Auf
    -0.22
     дух
    -0.22
     Höhen
    -0.22
     completely
    -0.22
     pure
    -0.22
    POSITIVE LOGITS
    RegressionTest
    0.78
    DockStyle
    0.77
     wireType
    0.75
    出版年
    0.73
    writeFieldEnd
    0.71
    WebElementEntity
    0.71
     témoig
    0.68
    OGND
    0.68
     disambiguazione
    0.68
    awtextra
    0.66
    Act Density 0.074%

    No Known Activations