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

    Neuronpedia

    INDEX
    Explanations

    embedding models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     忄
    0.43
     ét
    0.41
    közi
    0.39
    頭髮
    0.38
    ෙන
    0.38
    idavit
    0.38
    स्पद
    0.38
    ית
    0.37
    䔧
    0.37
    ีน
    0.37
    POSITIVE LOGITS
     embeds
    0.66
     embed
    0.65
     Embedding
    0.65
     Embed
    0.64
     embedding
    0.64
    嵌入
    0.62
     Embedded
    0.60
     embedded
    0.59
    Embed
    0.55
     embeddings
    0.53
    Act Density 0.010%

    No Known Activations