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

    Neuronpedia

    INDEX
    Explanations

    contribution guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    समझ
    0.45
     मोटापा
    0.45
    ിയത്
    0.43
    tri
    0.43
    diabetes
    0.43
     degeneracy
    0.42
     त्र
    0.42
    Mad
    0.42
     笑
    0.42
    愤怒
    0.42
    POSITIVE LOGITS
     Aeronaut
    0.45
     imprinted
    0.44
     infused
    0.43
     orice
    0.43
     sua
    0.42
     fato
    0.42
     firms
    0.41
     airfield
    0.41
    ভাবে
    0.40
     implanted
    0.40
    Act Density 0.002%

    No Known Activations