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

    Neuronpedia

    INDEX
    Explanations

    summarizing or describing concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.46
     with
    0.42
    比如
    0.41
     tới
    0.39
     vs
    0.39
     ("
    0.38
     to
    0.38
     >
    0.38
     Access
    0.37
     开始
    0.37
    POSITIVE LOGITS
     오늘도
    0.45
    และความ
    0.45
     undoubtedly
    0.44
     undeniably
    0.44
     enigmatic
    0.44
     remarkable
    0.43
    व्या
    0.43
     Schrö
    0.41
    pesar
    0.41
     некоторое
    0.41
    Act Density 0.055%

    No Known Activations