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

    Neuronpedia

    INDEX
    Explanations

    currency hedging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    çant
    0.48
    ya
    0.47
    hma
    0.46
    یا
    0.45
     तालिका
    0.43
    queda
    0.43
     аутох
    0.43
    én
    0.43
    acée
    0.43
    ština
    0.42
    POSITIVE LOGITS
     manufacturing
    0.49
    初めて
    0.48
    κει
    0.48
    「
    0.47
    Ð
    0.46
     first
    0.45
    factory
    0.45
     general
    0.45
    ↵
    0.44
     specify
    0.44
    Act Density 0.001%

    No Known Activations