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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Impl
    -0.08
     numerical
    -0.07
    𪩘
    -0.07
    沪
    -0.07
    集中
    -0.07
     thông
    -0.06
     ply
    -0.06
     planet
    -0.06
    uyến
    -0.06
    _dimension
    -0.06
    POSITIVE LOGITS
    ▭
    0.09
    hỏ
    0.08
    stantial
    0.07
    -saving
    0.07
    -thinking
    0.07
     BDS
    0.07
    .tk
    0.07
    石家
    0.07
     adequ
    0.07
    emark
    0.07
    Act Density 0.735%

    No Known Activations