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

    Neuronpedia

    INDEX
    Explanations

    live, living, lived

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.88
    rlig
    0.87
    ierte
    0.86
    NaN
    0.85
    ional
    0.84
     жителей
    0.84
    োগ
    0.84
    িয়ন
    0.83
     NaN
    0.83
    ér
    0.83
    POSITIVE LOGITS
     expectancy
    1.44
    wire
    1.32
     sót
    1.24
    blood
    1.15
    wires
    1.11
     Wage
    1.09
    WIRE
    1.05
    ्ह
    1.04
    泼
    1.03
    aboard
    1.02
    Act Density 0.120%

    No Known Activations