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

    Neuronpedia

    INDEX
    Explanations

    alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     palate
    0.20
     relent
    0.18
     oryg
    0.18
    న్‌
    0.17
     jeweiligen
    0.17
     trialComponents
    0.17
    <unused14>
    0.17
    ثنين
    0.17
    ัต
    0.16
     puisqu
    0.16
    POSITIVE LOGITS
     কিংবা
    0.31
     или
    0.30
     లేదా
    0.28
     alebo
    0.26
     oppure
    0.26
    或是
    0.26
    或者
    0.26
     অথবা
    0.26
     또는
    0.26
     veya
    0.25
    Act Density 1.073%

    No Known Activations