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

    Neuronpedia

    INDEX
    Explanations

    past situations and learning experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ieri
    0.82
     miliardi
    0.75
     milliseconds
    0.75
     trillions
    0.74
     coord
    0.73
     квадра
    0.73
    俑
    0.72
     infotainment
    0.72
     boomers
    0.71
     생성
    0.71
    POSITIVE LOGITS
     impoverished
    1.38
     exiled
    1.35
     apprent
    1.26
     apprenticeship
    1.25
     exile
    1.23
     poverty
    1.20
     tutoring
    1.12
    apprent
    1.12
     destitute
    1.11
     outcast
    1.08
    Act Density 0.093%

    No Known Activations