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

    Neuronpedia

    INDEX
    Explanations

    Championships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     livre
    -0.07
    慶
    -0.07
    燃
    -0.06
    #line
    -0.06
    .aspect
    -0.06
    Essay
    -0.06
     Dank
    -0.06
    办
    -0.06
     restraining
    -0.06
     sö
    -0.06
    POSITIVE LOGITS
    _PASSWORD
    0.07
    postgresql
    0.06
    Hospital
    0.06
    ilir
    0.06
     opráv
    0.06
    hon
    0.06
    _cfg
    0.06
    Mgr
    0.06
    Elect
    0.06
    Cream
    0.06
    Act Density 0.004%

    No Known Activations