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

    Neuronpedia

    INDEX
    Explanations

    don't worry or be shy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ployee
    0.73
     subordinates
    0.71
     laborer
    0.70
     staf
    0.66
     Worker
    0.65
     laborers
    0.64
     centrality
    0.64
     supremacy
    0.63
    ically
    0.63
    worker
    0.62
    POSITIVE LOGITS
     иллю
    0.67
     ιδια
    0.67
     яи
    0.66
     특히
    0.65
     embell
    0.65
     жесто
    0.65
     fret
    0.64
     quite
    0.64
     continueRoutine
    0.64
     গড়ে
    0.64
    Act Density 0.058%

    No Known Activations