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

    Neuronpedia

    INDEX
    Explanations

    reasons why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     civile
    0.52
     صہیونیت
    0.48
     रविदास
    0.45
    गीता
    0.45
     ट्रॉ
    0.44
     คํา
    0.42
     بیشتر
    0.42
     حمایت
    0.41
    renerg
    0.41
     tentativo
    0.41
    POSITIVE LOGITS
    唇
    0.46
    "]["
    0.45
    }=\
    0.44
    <li>
    0.43
    (<
    0.43
    州
    0.41
    故障
    0.41
    ${
    0.40
    ⺌
    0.40
    <0x89>
    0.39
    Act Density 0.004%

    No Known Activations