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

    Neuronpedia

    INDEX
    Explanations

    translation and linguistic concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.52
    2
    0.46
    0
    0.45
    ens
    0.42
    next
    0.42
    }{(
    0.42
     Palermo
    0.42
    7
    0.41
    တိုင်း
    0.41
    Next
    0.41
    POSITIVE LOGITS
    anlı
    0.50
    त्तीस
    0.47
     tolle
    0.47
     výraz
    0.47
    कल्पिक
    0.46
    少了
    0.46
     കുടും
    0.46
     socalled
    0.46
     mindre
    0.46
     zove
    0.46
    Act Density 0.002%

    No Known Activations