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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to programming and libraries

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

    linking libraries and directories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Phosph
    -0.38
     raiders
    -0.36
     raider
    -0.36
    pstmt
    -0.36
    terdam
    -0.35
    phosph
    -0.35
    Phosph
    -0.35
     оригіналу
    -0.34
    AntiForgery
    -0.34
     лю
    -0.33
    POSITIVE LOGITS
     beginnetje
    0.54
     propOrder
    0.54
     noDo
    0.53
    verwijspagina
    0.50
    ंदीखरीदारी
    0.50
    Autoritní
    0.50
     Италијани
    0.49
    TintMode
    0.49
    NameInMap
    0.48
    yntaxException
    0.47
    Act Density 0.152%

    No Known Activations