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

    Neuronpedia

    INDEX
    Explanations

    comparison functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    浯
    0.96
     outlay
    0.94
    漃
    0.91
     zooming
    0.88
    йся
    0.87
     Chab
    0.87
    лися
    0.87
    sı
    0.87
    𝑑
    0.86
    EMENT
    0.86
    POSITIVE LOGITS
    el
    1.03
     bactéri
    1.02
    istem
    1.00
     urč
    0.97
     lançamento
    0.96
     solução
    0.96
     této
    0.95
     terceiro
    0.95
     você
    0.95
     вероятно
    0.95
    Act Density 0.006%

    No Known Activations