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

    Neuronpedia

    INDEX
    Explanations

    convention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pay
    -0.08
     feeder
    -0.07
    rad
    -0.07
    SCR
    -0.07
    [next
    -0.06
    opened
    -0.06
     med
    -0.06
     miss
    -0.06
    _less
    -0.06
    .enterprise
    -0.06
    POSITIVE LOGITS
     Ottawa
    0.07
    惯例
    0.07
    热爱
    0.07
    _atom
    0.07
    Algorithm
    0.07
     habitats
    0.07
    .Collection
    0.07
    檔
    0.07
     limitation
    0.07
    /column
    0.06
    Act Density 0.024%

    No Known Activations