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

    Neuronpedia

    INDEX
    Explanations

    names of researchers and their respective affiliations or contributions

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

    Korea and Korean names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.45
     tolerant
    -0.34
    iomanip
    -0.34
     vis
    -0.33
    ђ
    -0.32
    ILLING
    -0.31
    setLong
    -0.30
     vene
    -0.30
     ben
    -0.30
     Här
    -0.29
    POSITIVE LOGITS
     Korea
    0.96
     Korean
    0.93
     Koreans
    0.91
    Korea
    0.87
    Korean
    0.85
     Seoul
    0.84
     Corée
    0.82
     coreana
    0.79
     korea
    0.79
    Seoul
    0.77
    Act Density 0.859%

    No Known Activations