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

    Neuronpedia

    INDEX
    Explanations

    software/device versioning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    canvas
    -0.06
    Semaphore
    -0.06
    marca
    -0.06
     Cumhuriyet
    -0.06
    .hasMore
    -0.06
     tacos
    -0.06
    51
    -0.06
    TestCategory
    -0.06
    stras
    -0.06
     gorgeous
    -0.06
    POSITIVE LOGITS
    遊
    0.07
     prezident
    0.06
     pubb
    0.06
    �
    0.06
    ヾ
    0.06
    ống
    0.06
    .mu
    0.06
    _elim
    0.06
    ichtet
    0.06
     Their
    0.06
    Act Density 0.030%

    No Known Activations