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

    Neuronpedia

    INDEX
    Explanations

    code structures involving iteration and condition checking

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

    Stack or queue operations (pop, dequeue)

    np_acts-logits-general · gemini-2.0-flash

    queue or stack operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    encodeWith
    -0.49
    galo
    -0.48
    SequentialGroup
    -0.46
    Sklici
    -0.45
     cherchés
    -0.45
    ียบ
    -0.44
    SetInt
    -0.44
     Coll
    -0.44
     spending
    -0.43
    ッセイ
    -0.42
    POSITIVE LOGITS
     dequeue
    0.79
    fromnode
    0.77
     pops
    0.76
    >{@
    0.76
     pop
    0.75
     CreateTagHelper
    0.75
    ReusableCell
    0.74
    pop
    0.73
    dequeue
    0.73
     popped
    0.71
    Act Density 0.352%

    No Known Activations