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

    Neuronpedia

    INDEX
    Explanations

    inch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    规章
    -0.07
    {j
    -0.07
     Clipboard
    -0.07
    号码
    -0.07
    核电
    -0.07
     Required
    -0.07
    ✗
    -0.06
     sideways
    -0.06
    刪
    -0.06
     arising
    -0.06
    POSITIVE LOGITS
    _CONVERT
    0.07
     belie
    0.07
     lẫn
    0.06
     ascertain
    0.06
    _PICK
    0.06
    找
    0.06
    ffiti
    0.06
    >",↵
    0.06
    izard
    0.06
     Bakan
    0.06
    Act Density 0.009%

    No Known Activations