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

    Neuronpedia

    INDEX
    Explanations

    hardware specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tomato
    0.74
     diuretic
    0.70
     lawn
    0.66
     prince
    0.65
     princess
    0.65
     chainsaw
    0.62
     Wochenende
    0.62
    iphone
    0.62
     tomatoes
    0.62
     fruitless
    0.62
    POSITIVE LOGITS
    支持
    0.98
     mendukung
    0.90
     支持
    0.90
     최대
    0.85
     Support
    0.84
     enhanced
    0.84
     DDR
    0.83
     stöd
    0.82
     hızlı
    0.81
     Enhanced
    0.81
    Act Density 0.208%

    No Known Activations