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

    Neuronpedia

    INDEX
    Explanations

    connecting parts or shop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    щению
    2.51
    わりに
    2.49
    щением
    2.45
    らう
    2.42
    щения
    2.39
     amma
    2.37
     diarrhoea
    2.30
     berjudul
    2.28
    円以上
    2.26
    ulkar
    2.26
    POSITIVE LOGITS
    º
    1.18
    quark
    1.16
     vibrational
    1.15
    7
    1.13
     inert
    1.13
     expectancy
    1.11
     bomber
    1.09
    formes
    1.06
     corps
    1.04
     separ
    1.03
    Act Density 0.289%

    No Known Activations