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

    Neuronpedia

    INDEX
    Explanations

    administrative references or categorization labels in a document

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

    End of turn marker

    np_acts-logits-general · gemini-2.0-flash

    legal documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.70
    Personensuche
    -0.60
     Савезне
    -0.59
     يتيمه
    -0.55
    featureID
    -0.55
    PreferredItem
    -0.54
    новништво
    -0.54
    Jereo
    -0.52
     sumpay
    -0.52
    AndView
    -0.52
    POSITIVE LOGITS
    odc
    0.41
     Hist
    0.38
     Jean
    0.33
    Hist
    0.33
    </tfoot>
    0.33
     AssemblyTitle
    0.32
     Mini
    0.31
     espon
    0.31
    fæ
    0.31
     nhi
    0.30
    Act Density 0.975%

    No Known Activations