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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming structures and operations, particularly in a threading context

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

    list indexing and iteration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.79
     Roskov
    -0.65
    httphttps
    -0.60
    RTSC
    -0.59
    <unused23>
    -0.57
    <unused14>
    -0.57
    <unused42>
    -0.57
    <unused79>
    -0.57
    <unused74>
    -0.57
    <pad>
    -0.57
    POSITIVE LOGITS
    DeleteMapping
    0.34
    ถ
    0.26
    SuppressMessage
    0.26
     wh
    0.25
    مراجع
    0.24
     Sho
    0.24
     double
    0.23
    erráneo
    0.23
    什么呢
    0.23
     autop
    0.22
    Act Density 0.026%

    No Known Activations