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

    Neuronpedia

    INDEX
    Explanations

    disclaimer at the end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Carlton
    0.44
    Está
    0.43
    ❧
    0.42
     esté
    0.41
    Cet
    0.40
    भारत
    0.39
    That
    0.38
    বিশ্ব
    0.38
    新
    0.38
    Ξ
    0.38
    POSITIVE LOGITS
    0.50
     […]
    0.48
     [...]
    0.45
    oglas
    0.42
     ```
    0.40
     ![](
    0.39
     阅读全文
    0.39
    0.38
    0.38
     ‚
    0.38
    Act Density 0.030%

    No Known Activations