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

    Neuronpedia

    INDEX
    Explanations

    references to classification and data structures within a technical context

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

    Code, systems, or technical jargon

    np_acts-logits-general · gemini-2.0-flash

    software, datasets, and algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↘
    -0.42
    tvguidetime
    -0.40
    ↗
    -0.40
    ंदीखरीदारी
    -0.40
     continue
    -0.40
     nahilalakip
    -0.40
     attention
    -0.39
     update
    -0.39
    setupUi
    -0.39
     dė
    -0.39
    POSITIVE LOGITS
    someone
    0.55
    eseorang
    0.54
     aDecoder
    0.52
     Seorang
    0.52
     iemand
    0.51
    somebody
    0.51
    mybatisplus
    0.50
     surla
    0.49
     informée
    0.48
     человеку
    0.48
    Act Density 0.644%

    No Known Activations