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

    Neuronpedia

    INDEX
    Explanations

    probability of ending a state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Province
    0.52
    含ま
    0.48
    هر
    0.48
    Taking
    0.44
     قدیمی
    0.42
     WERE
    0.42
    開業
    0.42
    CLEAR
    0.40
     province
    0.40
    Eli
    0.40
    POSITIVE LOGITS
    čkom
    0.47
    百
    0.46
     సామ
    0.46
    硬
    0.45
     용
    0.45
    anı
    0.45
     ноги
    0.44
    岌
    0.44
     준
    0.43
     ঘন
    0.43
    Act Density 0.000%

    No Known Activations