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

    Neuronpedia

    INDEX
    Explanations

    specific patterns and structures in scientific references or citations

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

    academic citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -1.09
    AddTagHelper
    -0.95
    Personensuche
    -0.91
    parsedMessage
    -0.87
    hoeddwyd
    -0.84
    principalColumn
    -0.82
    contentLoaded
    -0.82
    featureID
    -0.81
    -------------</
    -0.78
     propOrder
    -0.78
    POSITIVE LOGITS
     (
    0.38
    (
    0.32
    -
    0.31
    ↵
    0.29
     the
    0.28
    ↵↵
    0.28
     Bewer
    0.28
    ğını
    0.28
     [
    0.27
     hoş
    0.27
    Act Density 0.027%

    No Known Activations