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

    Neuronpedia

    INDEX
    Explanations

    multilingual text and specific programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    其他
    0.49
    现有
    0.46
     संदर्भ
    0.45
    阳
    0.45
    बा
    0.44
     паралле
    0.44
    其他人
    0.43
    计算
    0.43
    各类
    0.42
    બ
    0.42
    POSITIVE LOGITS
     very
    0.68
     equipments
    0.68
     amazingly
    0.66
     дуже
    0.64
    とても
    0.64
     helps
    0.63
     never
    0.62
     വളരെ
    0.62
     being
    0.61
     stimulates
    0.60
    Act Density 0.004%

    No Known Activations