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

    Neuronpedia

    INDEX
    Explanations

    specific types of command words or instructions, especially those associated with actions and decisions

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

    say the least

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.52
    abinieri
    -0.50
    脚注の使い方
    -0.50
    Lulu
    -0.50
    LoggerFactory
    -0.50
    发表于
    -0.49
    endphp
    -0.49
    ReusableCell
    -0.49
    weibo
    -0.49
    原始内容存档于
    -0.47
    POSITIVE LOGITS
     atve
    0.53
     reason
    0.48
     ainfi
    0.47
     înc
    0.47
     ولك
    0.46
     Таким
    0.44
     entanto
    0.44
     HttpNotFound
    0.43
     dezelve
    0.42
     vė
    0.42
    Act Density 0.132%

    No Known Activations