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

    Neuronpedia

    INDEX
    Explanations

    infrastructure, clean energy, jobs, investment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Literatura
    0.44
     representación
    0.43
     işlemi
    0.41
     letteratura
    0.41
    uradaki
    0.40
     dSample
    0.39
     Herpes
    0.39
     Drapeau
    0.38
     memeriksa
    0.38
     intervalos
    0.38
    POSITIVE LOGITS
    Biden
    0.56
    infrastructure
    0.55
     Biden
    0.52
     infrastructure
    0.48
     modernize
    0.47
    America
    0.46
    equity
    0.46
     revitalize
    0.46
     upgrade
    0.45
    upgrade
    0.45
    Act Density 0.001%

    No Known Activations