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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اجرا
    -0.06
     enforcement
    -0.06
    Parcel
    -0.06
    .learn
    -0.06
    Stan
    -0.06
     zaměstnan
    -0.06
    .Alter
    -0.06
     cinemas
    -0.06
     Rat
    -0.06
     punctuation
    -0.06
    POSITIVE LOGITS
     말
    0.07
     Mental
    0.07
     recursive
    0.06
     Immutable
    0.06
     wel
    0.06
     diet
    0.06
     regress
    0.06
     Calls
    0.06
     wis
    0.06
    accountId
    0.06
    Act Density 0.007%

    No Known Activations