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

    Neuronpedia

    INDEX
    Explanations

    before seeking different office

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Leben
    0.80
     પ્રાર્થના
    0.73
     meisten
    0.71
     Torque
    0.71
    Lint
    0.70
    ُ
    0.68
    Claude
    0.67
    π
    0.66
    ነት
    0.65
     जनते
    0.65
    POSITIVE LOGITS
    ější
    0.86
    ävät
    0.84
     брать
    0.83
     ancillary
    0.82
    ཙ
    0.79
     делать
    0.79
    тировать
    0.78
    ዚያ
    0.76
     inférieur
    0.75
    蹙
    0.75
    Act Density 0.001%

    No Known Activations