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

    Neuronpedia

    INDEX
    Explanations

    Months and days

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     me
    -0.07
    rets
    -0.06
    ej
    -0.06
     processor
    -0.06
    保障
    -0.06
    ください
    -0.06
      
↵
↵
    -0.06
     interpretations
    -0.06
    uhn
    -0.06
     Articles
    -0.06
    POSITIVE LOGITS
     setEmail
    0.07
    اعب
    0.07
    .ADD
    0.06
     Optim
    0.06
    justify
    0.06
    ुकस
    0.06
    .selected
    0.06
    ().'/
    0.06
     mannen
    0.06
    .Companion
    0.06
    Act Density 0.012%

    No Known Activations