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

    Neuronpedia

    INDEX
    Explanations

    reverse assembling or conserving storage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wm
    0.91
     ການ
    0.90
    pèce
    0.85
     による
    0.84
    䜌
    0.84
    ᄏ
    0.83
    CNc
    0.83
     مشتقه
    0.82
    鐗
    0.82
    ...”
    0.81
    POSITIVE LOGITS
     "
    0.54
     तल
    0.49
     e
    0.48
     Il
    0.46
    R
    0.44
    0.44
     P
    0.43
     list
    0.42
     Neighbour
    0.42
     de
    0.42
    Act Density 0.099%

    No Known Activations