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

    Neuronpedia

    INDEX
    Explanations

    foreign and modern concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ops
    0.47
     ソ
    0.47
     idol
    0.46
     अन्त
    0.46
    im
    0.45
     apple
    0.44
    醝
    0.44
    ran
    0.44
     sobres
    0.43
    aluronic
    0.43
    POSITIVE LOGITS
     bukan
    0.45
    近年
    0.45
     ähn
    0.44
     түр
    0.43
     França
    0.42
     modernen
    0.42
    А
    0.42
     иностран
    0.41
     thefe
    0.41
     ungew
    0.41
    Act Density 0.001%

    No Known Activations