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

    Neuronpedia

    INDEX
    Explanations

    ages and decades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rij
    0.69
    Places
    0.67
    ባት
    0.65
     kuru
    0.64
    aln
    0.62
     जा
    0.62
    ")]
    0.61
    "];
    0.59
    不然
    0.59
    тика
    0.59
    POSITIVE LOGITS
     twenties
    1.64
     thirties
    1.52
    xties
    1.38
     fifties
    1.32
    irties
    1.32
     sixties
    1.32
     teens
    1.31
     seventies
    1.28
    ineties
    1.27
     eighties
    1.23
    Act Density 0.091%

    No Known Activations