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

    Neuronpedia

    INDEX
    Explanations

    coding and programming-related terms and concepts

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

    "Stack" or related terms

    np_acts-logits-general · gemini-2.0-flash

    stack operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Guinée
    -0.59
     purpoſe
    -0.58
    ſelf
    -0.58
     Chriftian
    -0.57
     subdiv
    -0.57
     Shooter
    -0.56
     concerto
    -0.56
    HtmlAttribute
    -0.55
    :✨
    -0.55
     ainfi
    -0.54
    POSITIVE LOGITS
     stack
    1.18
    Stack
    1.10
     Stack
    1.08
    stack
    1.06
     STACK
    0.93
    STACK
    0.87
     stacks
    0.87
     Stacks
    0.83
    StackSize
    0.82
    Stacks
    0.81
    Act Density 0.153%

    No Known Activations