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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific symbols related to programming syntax

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

    user input following `<start_of_turn>`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="'.$
    -0.57
    MigrationBuilder
    -0.52
    '][$
    -0.48
    ='.$
    -0.46
    ="<?=$
    -0.45
    <?=$
    -0.45
    ='".$
    -0.43
    "=>$
    -0.42
    '=>$
    -0.42
    ","");
    -0.42
    POSITIVE LOGITS
     iprot
    0.52
     gekomen
    0.51
    出版年
    0.50
    neapolis
    0.50
    testify
    0.49
    InstrumentedTest
    0.49
    таратура
    0.49
     يتيمه
    0.49
     afhankelijk
    0.47
    SRP
    0.45
    Act Density 0.012%

    No Known Activations