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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    တွေကို
    0.30
    িবদ্ধ
    0.29
     হুমকির
    0.29
     공부해
    0.29
     લગભગ
    0.28
    ρους
    0.28
    齙
    0.27
     izango
    0.27
     Bathurst
    0.27
    aclysm
    0.27
    POSITIVE LOGITS
     one
    0.29
     perché
    0.27
    IN
    0.26
     because
    0.26
     ONE
    0.26
     یکی
    0.25
     needy
    0.25
    );
    0.24
     when
    0.24
     Zwei
    0.24
    Act Density 1.137%

    No Known Activations