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

    Neuronpedia

    INDEX
    Explanations

    programming-related structure elements and syntax

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

    optional and repeated fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.30
     indeed
    -0.30
    AutoModerator
    -0.29
     extranjero
    -0.27
    unconfirmed
    -0.24
     really
    -0.24
     Cualquier
    -0.23
    reportWebVitals
    -0.23
     bowiem
    -0.23
     cúp
    -0.23
    POSITIVE LOGITS
    Datuak
    0.89
     мәкал
    0.87
     estekak
    0.82
    InSection
    0.76
    <unused14>
    0.75
    <unused8>
    0.75
    <unused15>
    0.75
    <unused28>
    0.75
    <unused3>
    0.75
    [@BOS@]
    0.75
    Act Density 0.014%

    No Known Activations