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

    Neuronpedia

    INDEX
    Explanations

    entity owner or manager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    1.56
    غ
    1.50
    يت
    1.40
    ON
    1.35
    ला
    1.28
    naph
    1.27
    ائم
    1.26
     fevereiro
    1.26
     उत
    1.20
    나가
    1.20
    POSITIVE LOGITS
    lr
    1.30
    协会
    1.30
    ዎች
    1.27
     suro
    1.27
    ായി
    1.25
     реши
    1.20
    厂商
    1.17
    정도
    1.16
    ství
    1.13
     conséquences
    1.12
    Act Density 0.188%

    No Known Activations