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

    Neuronpedia

    INDEX
    Explanations

    later, less, much, from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rcode
    0.41
     bab
    0.39
     Babu
    0.38
    Ｂ
    0.38
     Bab
    0.37
     tip
    0.37
     nit
    0.37
    𝐵
    0.37
    sp
    0.36
     parc
    0.36
    POSITIVE LOGITS
     會
    0.42
     ఎమ్మె
    0.42
    走向
    0.39
    ைய
    0.38
    csvStream
    0.38
    الا
    0.37
    荖
    0.37
    </tbody>
    0.37
     नियुक्ति
    0.37
    ยี
    0.37
    Act Density 0.001%

    No Known Activations