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

    Neuronpedia

    INDEX
    Explanations

    the same regardless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    κτήθηκε
    0.55
    銷售
    0.46
     vendas
    0.45
    ഢ
    0.45
     ocasion
    0.44
    துவாக
    0.44
     cultivo
    0.44
    𝗯
    0.44
    ہور
    0.44
     vendita
    0.43
    POSITIVE LOGITS
    를
    0.48
    RE
    0.47
     downloaded
    0.47
     z
    0.45
     muted
    0.45
    ,
    0.44
     now
    0.44
     if
    0.44
    的前提
    0.43
     다음
    0.43
    Act Density 0.003%

    No Known Activations