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

    Neuronpedia

    INDEX
    Explanations

    marking a past starting point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     creates
    0.45
    மை
    0.45
     simulates
    0.44
     generates
    0.40
     prepares
    0.39
     stimulates
    0.39
     perceives
    0.37
     cityscape
    0.36
     می‌کند
    0.36
     地域
    0.36
    POSITIVE LOGITS
     منذ
    0.70
     since
    0.66
     sejak
    0.65
    Since
    0.60
     seit
    0.58
     Since
    0.57
     inception
    0.56
    since
    0.55
     óta
    0.55
    上次
    0.54
    Act Density 0.004%

    No Known Activations