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

    Neuronpedia

    INDEX
    Explanations

    dogs or tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    အတွက်
    0.35
     verpflicht
    0.35
     års
    0.34
     commemorating
    0.34
     hagg
    0.34
     keperluan
    0.34
     watercolour
    0.34
     produk
    0.34
     palvel
    0.34
     commemorative
    0.33
    POSITIVE LOGITS
     или
    0.56
     ή
    0.52
    或者
    0.47
    或
    0.46
    или
    0.43
     किंवा
    0.42
    或者是
    0.41
    或其他
    0.41
     یا
    0.41
     או
    0.39
    Act Density 0.002%

    No Known Activations