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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TW
    -0.10
     TW
    -0.09
     ముఖ్య
    -0.08
     ş
    -0.07
     ఆశ
    -0.07
     shumë
    -0.07
     pona
    -0.07
    chy
    -0.07
    (done
    -0.07
    ének
    -0.07
    POSITIVE LOGITS
     UTC
    0.08
    UTC
    0.08
     chauffeur
    0.08
    ட்டி
    0.07
    тации
    0.07
     berl
    0.07
    ண்ட
    0.07
    ண்டு
    0.07
     increments
    0.07
     milestones
    0.07
    Act Density 0.030%

    No Known Activations