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

    Neuronpedia

    INDEX
    Explanations

    as of today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Smart
    0.41
    Smart
    0.37
    nat
    0.36
     Intensity
    0.34
    ube
    0.34
     seaw
    0.34
    Ûn
    0.34
     intuitively
    0.34
    Localization
    0.34
     fake
    0.33
    POSITIVE LOGITS
     writing
    0.98
     लेखन
    0.90
     написа
    0.83
     लिखते
    0.82
     scrivere
    0.80
    寫
    0.78
    写作
    0.76
     kirjo
    0.75
     escrever
    0.75
     Writing
    0.74
    Act Density 0.022%

    No Known Activations