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

    Neuronpedia

    INDEX
    Explanations

    activate something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3.25
    𝐤
    2.89
     불구하고
    2.85
    টি
    2.76
     reversals
    2.74
     dealings
    2.74
    ுகிறது
    2.67
    घटना
    2.58
    eria
    2.56
    يد
    2.55
    POSITIVE LOGITS
    ade
    3.15
    ं
    3.10
    да
    2.99
    ق
    2.95
    し
    2.83
    ع
    2.80
    é
    2.79
    부터
    2.78
    ज
    2.75
    もら
    2.75
    Act Density 0.038%

    No Known Activations