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

    Neuronpedia

    INDEX
    Explanations

    size and length of collections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Town
    0.51
     Friends
    0.44
     Shelter
    0.44
     doanh
    0.44
     Consortium
    0.42
     Company
    0.42
     Secretary
    0.41
     apa
    0.41
     Appointments
    0.41
     Jack
    0.40
    POSITIVE LOGITS
    サイズ
    0.91
     size
    0.86
     Anzahl
    0.86
    size
    0.84
     sizes
    0.84
     length
    0.82
    Length
    0.82
     размер
    0.79
     gridSize
    0.78
     tamaños
    0.78
    Act Density 0.349%

    No Known Activations