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

    Neuronpedia

    INDEX
    Explanations

    facts being noted or established

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Obviously
    0.47
    Examples
    0.43
    Accessed
    0.41
    Think
    0.40
    Identifying
    0.39
     назвать
    0.39
    Declar
    0.38
    obviously
    0.38
    keywords
    0.37
     keywords
    0.37
    POSITIVE LOGITS
     noted
    0.73
     widely
    0.72
     diketahui
    0.61
     festgestellt
    0.58
     известно
    0.57
     выяс
    0.57
     установлено
    0.56
     conceded
    0.53
     stipulated
    0.51
     established
    0.49
    Act Density 0.006%

    No Known Activations