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

    Neuronpedia

    INDEX
    Explanations

    January and new year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     febru
    0.42
    Delimiter
    0.41
    秋
    0.40
    simeq
    0.40
    春
    0.40
    Feb
    0.39
     chce
    0.39
     februar
    0.39
     février
    0.38
    curly
    0.38
    POSITIVE LOGITS
     January
    0.84
     जनवरी
    0.75
     JANUARY
    0.75
    January
    0.75
    新年
    0.74
     Januari
    0.74
     jan
    0.73
     Jan
    0.69
     enero
    0.68
     JAN
    0.68
    Act Density 0.052%

    No Known Activations