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

    Neuronpedia

    INDEX
    Explanations

    modal verb + be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sagittis
    0.35
     తీసుకొ
    0.35
     зар
    0.34
     പ്രവര്‍
    0.34
     кел
    0.34
     generan
    0.34
    HEIM
    0.33
     ಸಾಕ
    0.32
    ารา
    0.32
     പ്രവർ
    0.32
    POSITIVE LOGITS
    itado
    0.34
     Acerca
    0.34
     einige
    0.32
     عدة
    0.31
    apons
    0.31
    rines
    0.30
    zioni
    0.30
    一定的
    0.29
    dns
    0.29
    بعض
    0.29
    Act Density 0.003%

    No Known Activations