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

    Neuronpedia

    INDEX
    Explanations

    rates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Liver
    -0.06
     Dict
    -0.06
    ext
    -0.06
    戏
    -0.06
     convict
    -0.06
    _TH
    -0.06
     beauty
    -0.06
    てい
    -0.06
    toi
    -0.06
     importer
    -0.06
    POSITIVE LOGITS
    DES
    0.06
    押
    0.06
     Instructions
    0.06
    \
↵
    0.06
    ��
    0.06
    ава
    0.06
     okhttp
    0.06
     Strike
    0.06
    (script
    0.06
    、《
    0.06
    Act Density 0.007%

    No Known Activations