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

    Neuronpedia

    INDEX
    Explanations

    references to mortality and related concepts

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

    身を守る手続き

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cenar
    -0.40
     ویکی‌پدی
    -0.39
     assault
    -0.38
     mídia
    -0.38
    らかに
    -0.38
     classic
    -0.37
     šo
    -0.36
     calça
    -0.36
     forcing
    -0.35
     murni
    -0.35
    POSITIVE LOGITS
     Anſ
    0.76
     Houſe
    0.66
    ſelves
    0.60
     Reſ
    0.58
     myſelf
    0.57
     queſta
    0.57
    MONEY
    0.56
    endphp
    0.56
    witzerland
    0.56
    perature
    0.55
    Act Density 0.051%

    No Known Activations