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

    Neuronpedia

    INDEX
    Explanations

    historical years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.64
     vuonna
    0.59
     circa
    0.56
    7
    0.56
     १९
    0.52
    1
    0.51
    9
    0.50
    8
    0.50
     ১৯৯
    0.50
     ২৯
    0.49
    POSITIVE LOGITS
     ancients
    0.49
    ዑ
    0.43
     calamities
    0.42
     interstices
    0.42
    पतवार
    0.41
    ત્રો
    0.41
     precincts
    0.40
     biosynthetic
    0.40
    สุ
    0.40
    耑
    0.40
    Act Density 0.011%

    No Known Activations