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

    Neuronpedia

    INDEX
    Explanations

    how to get

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     antiques
    0.45
     Retry
    0.39
     perce
    0.38
     garments
    0.38
    稞
    0.38
     switching
    0.38
     विक्रांत
    0.38
     cig
    0.37
     Lyndon
    0.37
    ഷേ
    0.37
    POSITIVE LOGITS
     саме
    0.40
    पाला
    0.38
    ел
    0.38
     بوده
    0.37
     dieser
    0.37
    August
    0.36
    вим
    0.36
     desta
    0.36
    Compound
    0.36
    Plot
    0.35
    Act Density 0.000%

    No Known Activations