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

    Neuronpedia

    INDEX
    Explanations

    developed nations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    れません
    0.42
    ным
    0.42
    ки
    0.41
    彧
    0.41
    閆
    0.40
    மய
    0.40
     verir
    0.40
    த்
    0.40
    ری
    0.39
     thủy
    0.39
    POSITIVE LOGITS
     reper
    0.52
    Wifi
    0.50
    }]
    0.49
    periode
    0.48
    WiFi
    0.47
    on
    0.46
    ោង
    0.46
     친
    0.45
     produc
    0.45
     gtag
    0.45
    Act Density 0.000%

    No Known Activations