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

    Neuronpedia

    INDEX
    Explanations

    comments and exceptions in programming code

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

    structured data and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    -0.38
    ↵↵
    -0.34
    Historique
    -0.33
     [
    -0.31
    <eos>
    -0.30
    .
    -0.29
     sur
    -0.29
    ↵
    -0.28
     AB
    -0.28
    早く
    -0.28
    POSITIVE LOGITS
    Personendaten
    0.88
     ujednoznacz
    0.85
     المعيارى
    0.84
     surla
    0.83
    AndEndTag
    0.82
     propOrder
    0.81
    parsedMessage
    0.79
    таратура
    0.77
    CloseOperation
    0.77
    RegressionTest
    0.74
    Act Density 0.036%

    No Known Activations