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

    Neuronpedia

    INDEX
    Explanations

    resource URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perspectives
    0.39
    各有
    0.38
     Wings
    0.36
     apathy
    0.34
    aS
    0.33
     Agents
    0.33
     polymeric
    0.33
     benefitting
    0.33
     benefit
    0.33
     பொரு
    0.33
    POSITIVE LOGITS
    녔
    0.37
    unati
    0.37
    Saat
    0.37
     recalculated
    0.37
    imdi
    0.37
    верса
    0.36
    unicode
    0.36
    ণাস্ত্র
    0.36
     เ
    0.35
    vur
    0.35
    Act Density 0.002%

    No Known Activations