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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Alternate
    -0.08
    唑
    -0.07
    劝
    -0.07
    sur
    -0.07
    demand
    -0.07
    Sample
    -0.06
    people
    -0.06
     instructional
    -0.06
     forcing
    -0.06
     BETWEEN
    -0.06
    POSITIVE LOGITS
    okit
    0.08
     무료
    0.08
     Tết
    0.07
    _FETCH
    0.07
    裂缝
    0.07
    孩子们
    0.06
    .setWindowTitle
    0.06
    这片
    0.06
     שניתן
    0.06
    包包
    0.06
    Act Density 0.066%

    No Known Activations