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

    Neuronpedia

    INDEX
    Explanations

    JSON key-value pairs and their corresponding structures

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

    JSON boolean and null values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.49
     חיצוניים
    -0.49
    Diwedd
    -0.48
     المعيارى
    -0.47
     invokingState
    -0.47
    AndEndTag
    -0.45
     CreateTagHelper
    -0.45
    Skocz
    -0.44
    Hochspringen
    -0.43
    MigrationBuilder
    -0.43
    POSITIVE LOGITS
    出版年
    0.51
    donald
    0.43
     CONTACT
    0.42
    @[+][
    0.41
    process
    0.41
    Process
    0.40
     process
    0.40
    txtName
    0.40
    newtheorem
    0.39
    FailureListener
    0.39
    Act Density 0.009%

    No Known Activations