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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assort
    -0.07
    玱
    -0.07
    Decoration
    -0.07
    簃
    -0.07
    ﴩ
    -0.07
     PT
    -0.07
     erfol
    -0.06
     MODE
    -0.06
    _FORE
    -0.06
     aprove
    -0.06
    POSITIVE LOGITS
     initialize
    0.08
    公务
    0.07
    扶
    0.07
    Old
    0.07
    UpDown
    0.07
    [href
    0.07
     skills
    0.07
     Former
    0.07
     *\
    0.07
    而不是
    0.07
    Act Density 0.004%

    No Known Activations