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

    Neuronpedia

    INDEX
    Explanations

    Providing information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     undermines
    -0.06
    ед
    -0.06
     imread
    -0.06
    包子
    -0.06
     comprehensive
    -0.06
     jungle
    -0.06
    ROME
    -0.06
    天堂
    -0.06
     Peace
    -0.06
     ali
    -0.06
    POSITIVE LOGITS
    それに
    0.07
    .openapi
    0.07
    tile
    0.07
    (/[
    0.07
     Wer
    0.07
    机器
    0.06
     glEnable
    0.06
    :!
    0.06
     attached
    0.06
    瓀
    0.06
    Act Density 0.100%

    No Known Activations