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

    Neuronpedia

    INDEX
    Explanations

    function calls and programming constructs in code snippets

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

    async function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.53
    endphp
    -0.48
     ſtand
    -0.47
    RegressionTest
    -0.47
     BoxDecoration
    -0.46
    ModelSerializer
    -0.45
     nonUne
    -0.44
     capuz
    -0.44
    featureID
    -0.44
    равда
    -0.44
    POSITIVE LOGITS
     individually
    0.49
     resourceCulture
    0.43
     individual
    0.41
    씩
    0.40
     individuellen
    0.38
     individuelle
    0.37
    setz
    0.35
     successively
    0.35
    individual
    0.35
     separately
    0.34
    Act Density 0.058%

    No Known Activations