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

    Neuronpedia

    INDEX
    Explanations

    for Foreign

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bonjour
    0.45
    zü
    0.45
    δα
    0.42
    াপনের
    0.42
    compens
    0.39
    नमस्कार
    0.39
     professora
    0.38
    蒙
    0.38
    ą
    0.38
    да
    0.37
    POSITIVE LOGITS
     လက်
    0.50
    ஓம்
    0.49
     पोर्ट
    0.48
     विक्रय
    0.48
     кілько
    0.47
     스타
    0.47
     beer
    0.47
    に行
    0.46
     kunde
    0.46
     zostać
    0.46
    Act Density 0.005%

    No Known Activations