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

    Neuronpedia

    INDEX
    Explanations

    structured step-by-step instructions or guidelines

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

    numbered steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.71
    ScopeManager
    -0.63
    localctx
    -0.61
    AddTagHelper
    -0.61
    setVerticalGroup
    -0.61
    fjspx
    -0.60
    tagext
    -0.60
     ModelExpression
    -0.59
    MigrationBuilder
    -0.59
     AssemblyCulture
    -0.58
    POSITIVE LOGITS
     steps
    0.50
    Steps
    0.47
     step
    0.47
    Step
    0.46
    第一步
    0.46
    step
    0.45
     langkah
    0.45
     Step
    0.44
    Bước
    0.43
     Steps
    0.43
    Act Density 0.014%

    No Known Activations