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

    Neuronpedia

    INDEX
    Explanations

    programming code structures and definitions

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

    final declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.59
    exitRule
    -0.46
    CreateModel
    -0.45
    AsUp
    -0.44
    tempor
    -0.43
    offsetof
    -0.43
     contextLoads
    -0.40
    ManyToMany
    -0.40
    <%=
    -0.40
    titleMargin
    -0.39
    POSITIVE LOGITS
     final
    0.47
     FINAL
    0.46
     Final
    0.45
    最终
    0.45
    最終
    0.45
     النها
    0.43
     readonly
    0.42
     sonunda
    0.42
     akhirnya
    0.41
     Akhir
    0.41
    Act Density 0.007%

    No Known Activations