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

    Neuronpedia

    INDEX
    Explanations

    Chinese greetings and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.48
    畨
    0.44
     लागि
    0.42
     সৌজন্য
    0.41
    运输
    0.40
    瓤
    0.40
    淝
    0.39
    Rim
    0.38
    )}$,
    0.38
    ありがとうございます
    0.38
    POSITIVE LOGITS
    цтва
    0.47
    imen
    0.45
     高さ
    0.45
     believers
    0.44
     นา
    0.44
     neutrons
    0.43
    }|
    0.42
     uglify
    0.42
     outcry
    0.42
     growth
    0.42
    Act Density 0.007%

    No Known Activations