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

    Neuronpedia

    INDEX
    Explanations

    yin and yang

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ===============↵
    -0.07
     sympt
    -0.07
     Demon
    -0.07
    즐
    -0.07
    .extend
    -0.06
    �
    -0.06
    .setUsername
    -0.06
     Recommendation
    -0.06
    Dr
    -0.06
     Slut
    -0.06
    POSITIVE LOGITS
    ,True
    0.07
    Stone
    0.07
    看出
    0.06
    Couldn
    0.06
    audio
    0.06
    準
    0.06
    _eof
    0.06
     אישי
    0.06
    Actually
    0.06
    坚
    0.06
    Act Density 0.018%

    No Known Activations