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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     strategy
    -0.08
     Craigslist
    -0.07
    ▷
    -0.07
     LOL
    -0.07
    小说
    -0.07
     pressures
    -0.07
    Disconnect
    -0.07
    <lemma
    -0.07
    \Collection
    -0.07
    鸫
    -0.07
    POSITIVE LOGITS
    _JO
    0.07
     ange
    0.07
    啖
    0.07
    IDA
    0.07
     educated
    0.07
    ("_
    0.07
     manned
    0.07
     visibly
    0.07
     hol
    0.06
    .detect
    0.06
    Act Density 0.023%

    No Known Activations