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

    Neuronpedia

    INDEX
    Explanations

    sequences related to categories and hierarchical classifications

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

    Category or technical list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    結
    -0.37
     ProtoMessage
    -0.36
     بيها
    -0.36
    DriverManager
    -0.35
     ddelweddau
    -0.33
    Населення
    -0.32
    isDead
    -0.32
    screen
    -0.32
     ε
    -0.31
    event
    -0.31
    POSITIVE LOGITS
    Personensuche
    0.56
     CreateTagHelper
    0.56
     AssemblyCompany
    0.54
     وتسجيلات
    0.54
     autorytatywna
    0.53
    aarrggbb
    0.53
     للمعارف
    0.52
    FieldOffsetTable
    0.51
    Хьажоргаш
    0.50
     мәкал
    0.49
    Act Density 0.045%

    No Known Activations