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

    Neuronpedia

    INDEX
    Explanations

    `Garlic` `harsh` `stark` `wolf`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्
    1.62
    ك
    1.58
    しっかりと
    1.38
    น
    1.30
    های
    1.28
    ล
    1.28
    ことです
    1.26
    ນ
    1.26
     Noch
    1.25
    ਾਰ
    1.24
    POSITIVE LOGITS
     GEN
    1.34
    ing
    1.30
    es
    1.30
    ەش
    1.30
    cü
    1.28
    重要的
    1.27
     snatch
    1.27
    一篇
    1.24
    ed
    1.23
    berra
    1.23
    Act Density 0.133%

    No Known Activations