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

    Neuronpedia

    INDEX
    Explanations

    holidays and special days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     behavior
    0.86
     behaviour
    0.75
     behaves
    0.70
    v
    0.68
     location
    0.66
     weight
    0.66
     mod
    0.65
    േഖ
    0.65
     variables
    0.65
     behaviors
    0.64
    POSITIVE LOGITS
     Día
    1.39
     Ngày
    1.34
    Halloween
    1.27
    День
    1.24
     Valentine
    1.24
    Valentines
    1.21
     Semana
    1.20
     Dünya
    1.19
    Birthday
    1.17
     Birthday
    1.17
    Act Density 0.022%

    No Known Activations