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

    Neuronpedia

    INDEX
    Explanations

    Family and children

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    registrer
    -0.08
     gratuitos
    -0.08
     económicos
    -0.08
    <Event
    -0.08
     definitive
    -0.08
    पत्र
    -0.07
     gratuite
    -0.07
     definit
    -0.07
     gratuit
    -0.07
    aires
    -0.07
    POSITIVE LOGITS
    父
    0.11
     부모
    0.10
     বাবা
    0.10
     father's
    0.10
     parents
    0.10
     माता
    0.10
    爸爸
    0.09
     Parents
    0.09
     traits
    0.09
    herited
    0.09
    Act Density 0.011%

    No Known Activations