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

    Neuronpedia

    INDEX
    Explanations

    functions, particularly those related to handling language and attributes in programming contexts

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

    Code-related syntax and punctuation

    np_acts-logits-general · gemini-2.0-flash

    `t.fail`, `t.equal`, `print(`, `BOOST_`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     B
    -0.55
     case
    -0.52
     J
    -0.46
    </b>
    -0.44
    qrstuvwxyz
    -0.43
    case
    -0.42
     M
    -0.42
    残り
    -0.41
    ДР
    -0.41
     do
    -0.41
    POSITIVE LOGITS
    __':
    0.89
    MigrationBuilder
    0.85
     متعلقه
    0.82
    writeFieldEnd
    0.82
     pinulongan
    0.77
    
    0.74
    OGND
    0.72
     оригіналу
    0.70
     autorytatywna
    0.69
    CloseOperation
    0.69
    Act Density 0.187%

    No Known Activations