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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guidelines and restrictions on sharing content

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

    instructions or commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.47
    <bos>
    -0.46
    -0.45
    ToScroll
    -0.45
    anglès
    -0.43
    liceerd
    -0.42
    ]=>
    -0.41
     تضيفلها
    -0.41
    antwoorde
    -0.40
     betweenstory
    -0.39
    POSITIVE LOGITS
     pleaſure
    0.55
    ſelf
    0.55
    expandindo
    0.53
    bibfield
    0.52
    GBK
    0.49
    bibinfo
    0.49
    期刊论文
    0.48
     myſelf
    0.48
     faſt
    0.47
     ſtate
    0.47
    Act Density 0.519%

    No Known Activations