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

    Neuronpedia

    INDEX
    Explanations

    uncertainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ypress
    -0.08
    每天
    -0.08
    няется
    -0.08
    ләре
    -0.08
     membutuhkan
    -0.07
     endlessly
    -0.07
     Seed
    -0.07
     Chaque
    -0.07
     Stamp
    -0.07
     proficiency
    -0.07
    POSITIVE LOGITS
     instead
    0.10
    Alternative
    0.09
    Maybe
    0.09
     istället
    0.09
    Alternate
    0.09
     reconsider
    0.09
    Instead
    0.09
    Let's
    0.08
    Incorrect
    0.08
     альтернатив
    0.08
    Act Density 0.037%

    No Known Activations