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

    Neuronpedia

    INDEX
    Explanations

    scientific studies and arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ھ
    -0.07
    诚
    -0.07
     nom
    -0.06
     stupidity
    -0.06
    之所以
    -0.06
    來自
    -0.06
    集团公司
    -0.06
    �
    -0.06
    屣
    -0.06
     Highlander
    -0.06
    POSITIVE LOGITS
     Displays
    0.07
     fireworks
    0.07
    FromBody
    0.07
    .keySet
    0.07
    database
    0.07
     Loot
    0.07
    coli
    0.07
    emarks
    0.07
    (',');↵
    0.07
     Morton
    0.07
    Act Density 0.003%

    No Known Activations