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

    Neuronpedia

    INDEX
    Explanations

    age in years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hingga
    0.77
     अधिकांश
    0.71
     correspond
    0.71
     έως
    0.69
     весьма
    0.66
    }}(-
    0.66
     perceptions
    0.65
     μέχρι
    0.65
     allotted
    0.64
     perceived
    0.64
    POSITIVE LOGITS
     old
    1.46
    old
    1.32
     olds
    1.12
     gamle
    0.96
     oude
    0.96
    OLD
    0.91
     vieille
    0.90
     vecchia
    0.87
     ancienne
    0.87
     long
    0.84
    Act Density 0.142%

    No Known Activations