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

    Neuronpedia

    INDEX
    Explanations

    actors' names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ̚
    0.48
    ter
    0.47
    っきり
    0.45
    Collectible
    0.44
    emplace
    0.44
    ère
    0.43
    äksi
    0.43
     GoObject
    0.42
     bū
    0.42
    ͆
    0.41
    POSITIVE LOGITS
     cinematography
    0.54
    ে
    0.50
    pielt
    0.48
    پردا
    0.48
     bantuan
    0.46
     skiing
    0.46
    𝖒
    0.45
     brilliantly
    0.45
     laureate
    0.44
     xgb
    0.44
    Act Density 0.008%

    No Known Activations