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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and data manipulation patterns

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

    code syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.64
     &___
    -0.53
    AccessorTable
    -0.53
    AddTagHelper
    -0.51
    offsetof
    -0.47
     चीज़ों
    -0.46
     düş
    -0.46
    +:+
    -0.45
    miş
    -0.44
     الرياضيه
    -0.44
    POSITIVE LOGITS
     فريبيس
    0.50
    Autoritní
    0.46
    хьтан
    0.44
     subsequently
    0.35
    Rohy
    0.35
     pair
    0.34
     ExecuteAsync
    0.34
     viață
    0.33
    __[
    0.33
    ValueGeneration
    0.32
    Act Density 0.002%

    No Known Activations