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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    НИ
    0.65
    ঙালি
    0.64
    ืช
    0.60
    óra
    0.60
     특집
    0.59
    원본파일명
    0.58
    Imagen
    0.58
    GoAbroad
    0.58
    imagem
    0.57
    Hozz
    0.57
    POSITIVE LOGITS
     two
    0.62
     difference
    0.54
     only
    0.53
     nine
    0.52
     $
    0.52
    two
    0.52
     differenza
    0.52
     intersection
    0.51
     seven
    0.50
     remaining
    0.50
    Act Density 0.003%

    No Known Activations