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

    Neuronpedia

    INDEX
    Explanations

    invent details or sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙢
    0.55
    IO
    0.54
    LAND
    0.48
    WriteString
    0.48
    阿拉伯
    0.48
    Request
    0.47
    IUM
    0.47
     исправ
    0.47
    ጦ
    0.47
    zm
    0.47
    POSITIVE LOGITS
     kiln
    0.45
     vinyl
    0.44
     pouring
    0.43
     しかし
    0.43
     vinegar
    0.42
     foyer
    0.42
     bi
    0.41
    ば
    0.41
     riverside
    0.41
     del
    0.41
    Act Density 0.002%

    No Known Activations