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

    Neuronpedia

    INDEX
    Explanations

    references to authority and guidance

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

    introducing a condition or consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.64
    цездатний
    -0.60
    AddTagHelper
    -0.56
    期刊论文
    -0.50
    ViewImports
    -0.49
    ViewFeatures
    -0.48
    InjectAttribute
    -0.46
    RegressionTest
    -0.44
    UrlResolution
    -0.43
    CppMethod
    -0.43
    POSITIVE LOGITS
    stdio
    0.47
    Saw
    0.43
    ."""
    0.42
    paddingVertical
    0.40
    }.
    0.40
    Europa
    0.39
    Switch
    0.39
    .")
    0.39
    Lud
    0.39
    Play
    0.39
    Act Density 0.173%

    No Known Activations