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

    Neuronpedia

    INDEX
    Explanations

    regular polygons and pyramids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    杜
    0.61
    ला
    0.58
    పి
    0.56
    涹
    0.55
    بە
    0.55
     Fond
    0.54
    เมื่อ
    0.52
    䣨
    0.52
     انٹر
    0.52
     Pursuant
    0.52
    POSITIVE LOGITS
    ות
    0.63
    anted
    0.58
    vertices
    0.58
     they
    0.56
    necklace
    0.56
    ם
    0.56
    pped
    0.54
     precipitate
    0.52
     trace
    0.52
    right
    0.51
    Act Density 0.007%

    No Known Activations