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

    Neuronpedia

    INDEX
    Explanations

    all-wheel drive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    f
    0.64
    ５
    0.57
    úde
    0.55
    ký
    0.52
    ，”
    0.52
    ｆ
    0.51
    >-</
    0.49
    aac
    0.49
    ваемые
    0.48
    。
    0.48
    POSITIVE LOGITS
    ش
    0.69
     snow
    0.55
    ש
    0.54
     leggere
    0.53
     sauv
    0.50
     سرد
    0.49
     bremsstrahlung
    0.49
     snowy
    0.49
     silice
    0.48
     גדול
    0.47
    Act Density 0.001%

    No Known Activations