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

    Neuronpedia

    INDEX
    Explanations

    duration of years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mayonnaise
    0.66
     Eigenschaften
    0.63
     bestimm
    0.62
     hallucinations
    0.61
     fries
    0.61
     items
    0.60
     makanan
    0.60
     button
    0.59
     Beispiel
    0.59
     неболь
    0.59
    POSITIVE LOGITS
     years
    1.87
    years
    1.77
     YEARS
    1.58
     Years
    1.57
    Years
    1.57
     decades
    1.44
    since
    1.44
     Jahren
    1.44
     વર્ષ
    1.44
     années
    1.41
    Act Density 0.008%

    No Known Activations