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

    Neuronpedia

    INDEX
    Explanations

    computation graph, friendship, grand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mondiale
    0.50
    uzzo
    0.49
    珬
    0.49
    Mua
    0.48
    𐰰
    0.47
    畱
    0.46
     ইলেক্ট্রোলাই
    0.46
    চা
    0.45
    സിൽ
    0.45
    hydrocèle
    0.44
    POSITIVE LOGITS
    0.55
     im
    0.47
     appealing
    0.44
     chipping
    0.42
     I
    0.41
     ornate
    0.41
    ρα
    0.40
     underline
    0.39
     alta
    0.39
    字体
    0.39
    Act Density 0.002%

    No Known Activations