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

    Neuronpedia

    INDEX
    Explanations

    key statistical measures and results in research studies

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

    relative measures and notable points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Commission
    -0.43
    PreExecute
    -0.43
     Commission
    -0.40
     comisión
    -0.38
    Revision
    -0.35
     indépend
    -0.35
     Wandel
    -0.35
     alianza
    -0.35
     nacional
    -0.35
     diputado
    -0.35
    POSITIVE LOGITS
     autorytatywna
    0.74
    Datuak
    0.73
     betweenstory
    0.72
    expandindo
    0.66
     kaarangay
    0.66
     &___
    0.64
     للاسماء
    0.63
     Мексичка
    0.60
    WithIOException
    0.59
     defaultstate
    0.58
    Act Density 0.161%

    No Known Activations