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

    Neuronpedia

    INDEX
    Explanations

    expressions of quantitative data or statistics

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

    numbers and dollar amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.64
     Италијани
    -0.63
     Administrativna
    -0.56
     Мексичка
    -0.54
     ویکی‌پدی
    -0.54
    ьаж
    -0.52
     INTERESAR
    -0.52
     <>",
    -0.51
    点此举报
    -0.50
     мәкалә
    -0.48
    POSITIVE LOGITS
    0
    0.74
    2
    0.41
    that
    0.36
    centes
    0.35
     hadn
    0.35
    ÁT
    0.35
    Don
    0.34
    tonode
    0.34
    toso
    0.34
    coden
    0.34
    Act Density 0.015%

    No Known Activations