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

    Neuronpedia

    INDEX
    Explanations

    categories and context related to politics and championships

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

    list format (abbreviations, definitions)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Witam
    -0.29
     iesp
    -0.29
     required
    -0.28
     Bearbeitung
    -0.27
     efficiently
    -0.27
    Witaj
    -0.27
     principle
    -0.26
     consistently
    -0.26
     encargada
    -0.25
     specialized
    -0.25
    POSITIVE LOGITS
    httphttps
    0.98
     otomatig
    0.90
    Personendaten
    0.88
    GEBURTS
    0.88
    ValueStyle
    0.85
     يتيمه
    0.82
     pinulongan
    0.77
    ьаж
    0.73
     estekak
    0.72
     ModelExpression
    0.72
    Act Density 0.007%

    No Known Activations