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

    Neuronpedia

    INDEX
    Explanations

    embedded within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    যথ
    0.69
    점
    0.67
    ಮಾರ
    0.59
    缺少
    0.58
     ميل
    0.58
    ಸ್ಪ
    0.58
     đoán
    0.56
     sağlam
    0.55
     diminta
    0.55
    점에서
    0.55
    POSITIVE LOGITS
     embedded
    3.73
    embedded
    3.18
     Embedded
    3.04
     embed
    2.88
    Embedded
    2.87
     embedding
    2.69
    嵌入
    2.64
     embeds
    2.58
     encased
    2.47
     Embedding
    2.43
    Act Density 0.946%

    No Known Activations