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

    Neuronpedia

    INDEX
    Explanations

    SQL query commands and keywords

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

    SQL SELECT statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BorderRadius
    -0.47
    ุ
    -0.39
    WEBPACK
    -0.38
     plans
    -0.37
     helped
    -0.35
     GlobalKey
    -0.35
    ỡng
    -0.34
    -
    -0.34
    <eos>
    -0.34
     being
    -0.34
    POSITIVE LOGITS
    SELECT
    0.75
    SequentialGroup
    0.65
    ftagPool
    0.65
    select
    0.57
    indd
    0.56
     selectAll
    0.55
    makeConstraints
    0.54
    tagPool
    0.54
     SELECT
    0.54
    LabelTagHelper
    0.53
    Act Density 0.005%

    No Known Activations