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

    Neuronpedia

    INDEX
    Explanations

    currency amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kot
    0.68
     चतुर्थ
    0.64
     necessarily
    0.62
     rectangular
    0.62
    elementary
    0.59
     elementary
    0.59
    不妨
    0.58
     velcro
    0.58
     عدد
    0.58
     Elementary
    0.57
    POSITIVE LOGITS
     বেড়ে
    0.78
     légèrement
    0.78
    boden
    0.75
     чуть
    0.71
     ભાવ
    0.71
    略
    0.71
    പ്പം
    0.71
    चा
    0.68
     नाबाद
    0.66
    €
    0.65
    Act Density 0.508%

    No Known Activations