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

    Neuronpedia

    INDEX
    Explanations

    the place to find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    興
    0.53
    ใจ
    0.49
    心
    0.44
    EntryPoint
    0.43
    ทำ
    0.43
    車
    0.41
     heart
    0.41
    內的
    0.41
    พ
    0.40
    มห
    0.40
    POSITIVE LOGITS
    тон
    0.53
     correcto
    0.50
     correto
    0.47
     göster
    0.47
    whenever
    0.46
     fonctionner
    0.46
    சார்
    0.46
    corrected
    0.46
    ках
    0.45
     चार्
    0.43
    Act Density 0.003%

    No Known Activations