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

    Neuronpedia

    INDEX
    Explanations

    multilingual greetings and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sciences
    0.50
    Carbon
    0.48
    צב
    0.47
    Исход
    0.47
    Extensions
    0.45
    Einstellungen
    0.45
    خط
    0.42
    Variants
    0.41
    خاص
    0.41
    Fred
    0.41
    POSITIVE LOGITS
     तुम्ही
    0.56
     是
    0.48
     tôi
    0.46
     मैं
    0.45
    我知道
    0.45
     yǒu
    0.44
     थोड़ी
    0.43
     je
    0.42
     hãy
    0.42
     Rescue
    0.42
    Act Density 0.013%

    No Known Activations