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

    Neuronpedia

    INDEX
    Explanations

    federal government and finance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     клет
    0.64
     excluir
    0.63
     jīn
    0.63
     автомобиль
    0.62
     eléctrica
    0.61
     Jat
    0.61
     manchas
    0.61
     defini
    0.60
     tinta
    0.60
     вече
    0.59
    POSITIVE LOGITS
    Еще
    0.75
    าน
    0.63
    u
    0.63
    æ
    0.59
    명
    0.58
    Eine
    0.57
    극
    0.57
    Trước
    0.57
    SH
    0.56
    x
    0.55
    Act Density 0.002%

    No Known Activations