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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords in code snippets

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

    javascript imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dAtA
    -0.70
     autorytatywna
    -0.65
    +#+#
    -0.57
     &___
    -0.57
    parsedMessage
    -0.54
    ंदीखरीदारी
    -0.54
    principalColumn
    -0.53
    Autoritní
    -0.51
    Diwedd
    -0.47
    клопе
    -0.47
    POSITIVE LOGITS
    جمعیت
    0.42
     تضيفلها
    0.40
    hésite
    0.38
     متعلقه
    0.36
    はじめに
    0.35
    VAO
    0.35
    BeginInit
    0.35
     урна
    0.35
     شاهد
    0.35
    findpost
    0.35
    Act Density 0.005%

    No Known Activations