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

    Neuronpedia

    INDEX
    Explanations

    quoted text opener

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ன்ப
    0.63
    okhttp
    0.58
    ième
    0.57
    𝐞
    0.55
    ভুক্ত
    0.55
    aka
    0.55
    ✽
    0.54
     excitatory
    0.54
    логии
    0.54
    ృష్ణ
    0.54
    POSITIVE LOGITS
     Может
    0.62
    मिटेड
    0.59
    )}.
    0.58
    З
    0.58
    git
    0.58
    \")
    0.57
    }");
    0.57
     pid
    0.56
    ﻪ
    0.55
    ت
    0.54
    Act Density 0.223%

    No Known Activations