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

    Neuronpedia

    INDEX
    Explanations

    phrases related to improvement and addressing needs

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

    improvement and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.62
    CppMethod
    -0.61
     Lightboxes
    -0.61
    GraphicsUnit
    -0.59
    HtmlAttribute
    -0.59
    aarrggbb
    -0.59
     glut
    -0.54
    Билгалдахарш
    -0.54
    telles
    -0.53
     Италијани
    -0.52
    POSITIVE LOGITS
     виправи
    0.43
     sağlay
    0.42
     powietrza
    0.39
     Feinde
    0.38
     neuem
    0.36
    を変更
    0.35
    を変える
    0.35
     leggen
    0.35
    改进
    0.35
     change
    0.34
    Act Density 0.029%

    No Known Activations