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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

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

    expression of gratitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تفصیلات
    -0.44
    ValueGenerated
    -0.43
    stylers
    -0.40
     LIK
    -0.38
    antd
    -0.37
     ulaş
    -0.37
    diğinde
    -0.37
    rari
    -0.37
     neighbouring
    -0.37
    ctos
    -0.36
    POSITIVE LOGITS
    MemoryWarning
    0.60
    abestanden
    0.53
    HomeAsUpEnabled
    0.50
     informée
    0.50
     GenerationType
    0.50
    Portail
    0.50
     فريبيس
    0.49
    脚注の使い方
    0.49
    printStackTrace
    0.49
    expandindo
    0.49
    Act Density 0.024%

    No Known Activations