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

    Neuronpedia

    INDEX
    Explanations

    characters and components related to user privacy and verification in online settings

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

    language and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserScript
    -0.38
    、
    -0.35
    /
    -0.35
    ↵↵↵
    -0.35
     Nach
    -0.35
    ByPrimaryKey
    -0.34
     Alas
    -0.34
     blend
    -0.33
    izza
    -0.33
     woes
    -0.33
    POSITIVE LOGITS
     dieß
    0.78
     laſſen
    0.71
     kasarigan
    0.69
     ویکی‌پدی
    0.69
    parsedMessage
    0.68
     للمعارف
    0.66
     dieſes
    0.65
    errHandler
    0.65
     typelib
    0.63
     CreateTagHelper
    0.63
    Act Density 0.012%

    No Known Activations