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

    Neuronpedia

    INDEX
    Explanations

    Ukrainian and Russian words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ഗെയി
    0.47
    σή
    0.46
    યોગ
    0.45
     الحكم
    0.45
    الحكم
    0.45
    zték
    0.45
    詈
    0.45
    சா
    0.44
    ಪಟ್ಟ
    0.43
    ჯერ
    0.43
    POSITIVE LOGITS
    ut
    0.41
    ist
    0.41
    ests
    0.40
    apolis
    0.40
    ap
    0.39
     ทาง
    0.38
     restores
    0.38
     TUN
    0.38
    ient
    0.38
    athione
    0.38
    Act Density 0.041%

    No Known Activations