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

    Neuronpedia

    INDEX
    Explanations

    code formatting and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Reading
    0.54
    Reading
    0.51
     Readings
    0.50
    रासत
    0.47
    Resource
    0.47
     Recorded
    0.46
    шымта
    0.46
     Resource
    0.46
    ឧបករណ៍
    0.46
     Delivered
    0.46
    POSITIVE LOGITS
     평
    0.62
     따라
    0.60
     바
    0.58
     원
    0.58
     타
    0.57
     검색
    0.57
     전문가
    0.56
     버
    0.56
     라
    0.56
     추천
    0.55
    Act Density 0.060%

    No Known Activations