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

    Neuronpedia

    INDEX
    Explanations

    transformed into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    čin
    0.57
    Ⴊ
    0.54
    ajjati
    0.52
    kken
    0.52
    рения
    0.52
    atzen
    0.52
    antown
    0.52
     Retrieved
    0.51
    させる
    0.50
    etches
    0.50
    POSITIVE LOGITS
     by
    0.68
     بواسطة
    0.64
     oleh
    0.59
     outfitted
    0.58
     decked
    0.55
     pomocí
    0.55
     chock
    0.53
     accordingly
    0.52
    by
    0.52
     up
    0.51
    Act Density 0.000%

    No Known Activations