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

    Neuronpedia

    INDEX
    Explanations

    Access to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्रू
    0.43
    xcuser
    0.42
    xyplot
    0.39
     cottura
    0.39
    imidazo
    0.39
     seluruh
    0.38
     نباش
    0.38
    myY
    0.38
     亠
    0.37
     dama
    0.37
    POSITIVE LOGITS
     aur
    0.37
     Sten
    0.37
     digitalization
    0.37
    Gabriel
    0.37
     tâm
    0.36
    啉
    0.36
     শিব
    0.36
     Wij
    0.35
     podia
    0.35
    詫
    0.35
    Act Density 0.002%

    No Known Activations