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

    Neuronpedia

    INDEX
    Explanations

    exact wording or name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     How
    0.42
     presupp
    0.41
     Suppose
    0.40
    भूत
    0.39
     Assume
    0.39
     व्यवहार
    0.39
     Assuming
    0.39
     oneself
    0.38
     presumably
    0.38
     implying
    0.37
    POSITIVE LOGITS
     name
    0.67
    的名字
    0.61
    名字
    0.61
    名稱
    0.58
    name
    0.54
     название
    0.54
    名称
    0.53
     названия
    0.53
     имена
    0.52
     nombre
    0.50
    Act Density 0.048%

    No Known Activations