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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Porn
    -0.07
     Garr
    -0.07
     millennia
    -0.07
    remen
    -0.06
    严
    -0.06
     Plays
    -0.06
     applicants
    -0.06
     Dou
    -0.06
    一下子
    -0.06
     Encoder
    -0.06
    POSITIVE LOGITS
    lasses
    0.08
    opic
    0.07
    記事
    0.07
     ];↵
    0.07
    _Surface
    0.06
    trip
    0.06
    (T
    0.06
    iation
    0.06
     가지고
    0.06
     onChange
    0.06
    Act Density 0.049%

    No Known Activations