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

    Neuronpedia

    INDEX
    Explanations

    future financial goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -
    0.52
    arch
    0.46
     breadth
    0.46
    us
    0.45
    key
    0.45
    node
    0.44
    ks
    0.44
    ending
    0.43
    ka
    0.42
    0.41
    POSITIVE LOGITS
     toekom
    0.62
     미래
    0.61
     будущем
    0.59
     toekomst
    0.57
    未来的
    0.55
    未来
    0.55
     futuros
    0.55
    未來
    0.53
     ভবিষ্যত
    0.53
    将来
    0.53
    Act Density 0.002%

    No Known Activations