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

    Neuronpedia

    INDEX
    Explanations

    phases and timeframes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    目录
    0.41
    复杂的
    0.36
    较高的
    0.36
     directory
    0.35
     hommage
    0.35
    lja
    0.34
    纽
    0.34
    rous
    0.34
    录
    0.34
     ज्यो
    0.34
    POSITIVE LOGITS
     immediate
    0.97
    immediate
    0.96
     inmediata
    0.88
     IMMEDIATE
    0.87
    半年
    0.85
    Immediate
    0.84
     imedi
    0.83
     Months
    0.81
    短期
    0.80
     immédi
    0.80
    Act Density 0.051%

    No Known Activations