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

    Neuronpedia

    INDEX
    Explanations

    next word or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puisque
    0.46
     కాల
    0.42
    торое
    0.40
     yksi
    0.40
    కాల
    0.39
     ổ
    0.39
     ży
    0.38
     Chưa
    0.38
     όχι
    0.38
    ۝
    0.38
    POSITIVE LOGITS
    next
    0.56
     next
    0.47
    Next
    0.42
    NEXT
    0.41
    sometimes
    0.41
    Front
    0.40
    front
    0.39
     다음에
    0.39
    however
    0.39
    다음
    0.39
    Act Density 0.000%

    No Known Activations