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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    报告期内
    -0.09
     datastore
    -0.07
    -min
    -0.07
    /public
    -0.07
    ibble
    -0.07
    _rand
    -0.07
    StorageSync
    -0.07
    盂
    -0.07
    _err
    -0.07
    `${
    -0.07
    POSITIVE LOGITS
    ♮
    0.08
    维奇
    0.08
    -cross
    0.07
    求婚
    0.07
    lli
    0.07
     mating
    0.07
    önü
    0.07
     Auch
    0.07
    OfType
    0.07
    .solve
    0.07
    Act Density 0.174%

    No Known Activations