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

    Neuronpedia

    INDEX
    Explanations

    Periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inflammatory
    -0.07
    concert
    -0.07
    maf
    -0.07
    ید
    -0.06
     baking
    -0.06
     Pur
    -0.06
     wine
    -0.06
     drowning
    -0.06
     पद
    -0.06
    .tech
    -0.06
    POSITIVE LOGITS
     깨
    0.06
     Orient
    0.06
    Οι
    0.06
    .sorted
    0.06
     domestically
    0.06
     mümkün
    0.06
     cheesy
    0.06
    .st
    0.06
     tweet
    0.06
    irates
    0.06
    Act Density 0.030%

    No Known Activations