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

    Neuronpedia

    INDEX
    Explanations

    bullet points or numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ael
    0.38
     dil
    0.37
     [...
    0.35
     del
    0.35
     LAN
    0.34
    减
    0.34
    SEL
    0.33
     waarin
    0.33
     pir
    0.33
    简称
    0.32
    POSITIVE LOGITS
    ifes
    0.38
    चीन
    0.37
     αγο
    0.35
    同じ
    0.34
     μό
    0.34
     खूप
    0.34
     อาท
    0.34
     ओबीसी
    0.34
     дополнительных
    0.33
    兗
    0.33
    Act Density 0.002%

    No Known Activations