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

    Neuronpedia

    INDEX
    Explanations

    what are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     प्लांट्स
    0.44
    larini
    0.44
     *=
    0.42
    polymer
    0.41
    name
    0.41
     Remembering
    0.41
    িনীর
    0.40
    rm
    0.40
    styles
    0.40
    till
    0.39
    POSITIVE LOGITS
    ató
    0.46
     సై
    0.45
     الصحية
    0.44
    énés
    0.43
     তোলে
    0.43
     하지
    0.42
     gebaut
    0.42
     sá
    0.41
     다섯
    0.40
     وي
    0.40
    Act Density 0.002%

    No Known Activations