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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and references

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

    Vernon Supp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.75
     мәкал
    -0.71
    Попис
    -0.71
     незавершена
    -0.70
     Numerade
    -0.69
     Мексичка
    -0.63
    oa̍t
    -0.62
    Географиясе
    -0.62
    :✨
    -0.61
    المناصب
    -0.60
    POSITIVE LOGITS
    Text
    0.60
     text
    0.54
     Text
    0.49
    text
    0.48
    Word
    0.39
     текст
    0.39
     
    0.35
     building
    0.34
     word
    0.34
     chữ
    0.34
    Act Density 0.001%

    No Known Activations