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

    Neuronpedia

    INDEX
    Explanations

    resort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    2.06
    करण
    2.00
    र
    1.84
    ם
    1.84
     wives
    1.80
     sweetheart
    1.80
    ுள்ளது
    1.73
    可以
    1.71
     superlative
    1.70
     apartment
    1.66
    POSITIVE LOGITS
    те
    2.94
    ни
    2.91
    다
    2.86
    i
    2.44
    iendo
    2.41
    urile
    2.28
    licts
    2.28
    ه
    2.17
    おります
    2.08
    槁
    2.05
    Act Density 0.003%

    No Known Activations