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

    Neuronpedia

    INDEX
    Explanations

    sections of code with significant control flow structures like conditional statements and loops

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

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.58
    ↵↵
    -0.53
     and
    -0.41
    <eos>
    -0.40
    [
    -0.40
    "
    -0.38
    <strong>
    -0.38
     Additionally
    -0.37
    ↵
    -0.37
     #
    -0.36
    POSITIVE LOGITS
    setVerticalGroup
    1.12
    parsedMessage
    1.11
    __":
    1.05
     CreateTagHelper
    1.04
    1.02
     autorytatywna
    1.01
    tagHelperRunner
    1.00
    RenderAtEndOf
    1.00
     كومونز
    1.00
    __':
    1.00
    Act Density 0.016%

    No Known Activations