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

    Neuronpedia

    INDEX
    Explanations

    lists and empty structures in programming contexts

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

    list initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.86
    [@BOS@]
    -0.68
    <unused14>
    -0.68
    <unused52>
    -0.68
    <unused16>
    -0.68
    <unused3>
    -0.68
    <unused41>
    -0.68
    <unused51>
    -0.68
    <unused42>
    -0.68
    <unused17>
    -0.67
    POSITIVE LOGITS
    =[]
    0.36
    List
    0.29
    L
    0.28
     Procu
    0.28
     compositeur
    0.27
     StatelessWidget
    0.27
    list
    0.27
    ()
    0.26
     procès
    0.26
     list
    0.25
    Act Density 0.002%

    No Known Activations