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

    Neuronpedia

    INDEX
    Explanations

    high blood levels causing issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ార
    0.40
     комплек
    0.37
    EVER
    0.37
    awed
    0.36
    ້ງ
    0.35
    Routine
    0.35
    Careers
    0.34
    ασ
    0.34
     완성
    0.34
    中国的
    0.34
    POSITIVE LOGITS
     eccess
    0.43
     influx
    0.43
     imbalance
    0.43
     nguy
    0.42
     exces
    0.42
     tuj
    0.42
     alarm
    0.41
     alert
    0.41
     harmful
    0.41
     excess
    0.40
    Act Density 0.005%

    No Known Activations