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

    Neuronpedia

    INDEX
    Explanations

    investments in self or infrastructure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contribution
    0.50
     contribution
    0.47
     Contributions
    0.46
     contributions
    0.43
     Contribution
    0.43
     योगदान
    0.41
     CONTRIBUTION
    0.41
    贡献
    0.39
     contributo
    0.39
     Newly
    0.38
    POSITIVE LOGITS
     invest
    0.70
     infrastructure
    0.69
     infraestructura
    0.58
     infrast
    0.57
     infrastrukt
    0.56
    Invest
    0.55
     yatırım
    0.55
     investasi
    0.55
    基础设施
    0.54
     investment
    0.54
    Act Density 0.004%

    No Known Activations