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

    Neuronpedia

    INDEX
    Explanations

    compound, rejected, import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    延长
    0.42
     Draco
    0.41
    发动
    0.38
    comma
    0.38
    ider
    0.37
     Bilal
    0.37
    ще
    0.36
    曼
    0.36
    elected
    0.36
     فاس
    0.36
    POSITIVE LOGITS
     years
    0.47
     metų
    0.47
     sayısı
    0.42
     संख्या
    0.42
     χρόνια
    0.41
    म्मेदारी
    0.40
     días
    0.40
     roky
    0.40
     meses
    0.39
     nights
    0.39
    Act Density 0.000%

    No Known Activations