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

    Neuronpedia

    INDEX
    Explanations

    function Calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    str
    0.42
     i
    0.41
     cultures
    0.40
     Dalai
    0.40
     honours
    0.40
     चर्चित
    0.39
     সময়
    0.39
     anos
    0.39
     Tibetan
    0.38
    linux
    0.38
    POSITIVE LOGITS
    年龄
    0.48
    끔
    0.47
    하는데
    0.47
    itoare
    0.46
    சிற
    0.45
    제곱
    0.45
    itek
    0.44
    这样的
    0.44
    äle
    0.44
    이버
    0.44
    Act Density 0.032%

    No Known Activations