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

    Neuronpedia

    INDEX
    Explanations

    costs and needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trấn
    0.55
     obtenir
    0.52
     coughing
    0.51
     способом
    0.50
     whether
    0.47
     intentar
    0.47
     Zhe
    0.47
     специфи
    0.47
     زمین
    0.46
     roupas
    0.46
    POSITIVE LOGITS
    大手
    0.42
    ISA
    0.41
    на
    0.38
    ز
    0.37
    ₪
    0.37
    ρθρο
    0.37
    自我
    0.37
    isetas
    0.37
    ಣ
    0.37
    زوج
    0.35
    Act Density 0.001%

    No Known Activations