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

    Neuronpedia

    INDEX
    Explanations

    references to data structure types and initialization methods in programming

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

    object initializers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bet
    -0.32
     $\
    -0.27
     
    -0.25
    .
    -0.25
     (
    -0.25
     so
    -0.24
     sti
    -0.24
    twór
    -0.24
    Rhestr
    -0.24
    $\
    -0.24
    POSITIVE LOGITS
    instancetype
    1.31
    expanded
    1.14
     kasarigan
    0.99
    出版年
    0.94
    HasColumnType
    0.89
     Expanded
    0.88
    parsedMessage
    0.87
     estekak
    0.86
     autorytatywna
    0.85
    ollectionView
    0.84
    Act Density 0.002%

    No Known Activations