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

    Neuronpedia

    INDEX
    Explanations

    physical or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     যখন
    0.47
     የታ
    0.47
     담
    0.46
    OfWeek
    0.44
     아무
    0.44
     겨울
    0.44
     εκ
    0.44
    炆
    0.43
     госпо
    0.42
     გამ
    0.42
    POSITIVE LOGITS
    юра
    0.50
    ляр
    0.47
     poza
    0.46
    做
    0.46
     saúde
    0.46
    飯店
    0.46
     més
    0.45
    на
    0.45
    кова
    0.45
     Pasand
    0.45
    Act Density 0.000%

    No Known Activations