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

    Neuronpedia

    INDEX
    Explanations

    AI concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ését
    0.52
    MODKEY
    0.51
     எழுதிய
    0.49
    achem
    0.48
    ő
    0.48
    arpur
    0.47
    AVES
    0.47
    나가
    0.45
     왜
    0.44
    नामा
    0.44
    POSITIVE LOGITS
     QQ
    0.47
     Tsun
    0.46
     Moovit
    0.46
     بسيطه
    0.46
     Marques
    0.45
     communication
    0.44
     لوبو
    0.43
     lieben
    0.43
     صعبه
    0.43
     Nast
    0.43
    Act Density 0.000%

    No Known Activations