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

    Neuronpedia

    INDEX
    Explanations

    how much/many

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    方式
    0.59
     manner
    0.54
     manière
    0.54
     način
    0.53
     spôsob
    0.52
     maniera
    0.51
     ways
    0.50
     방식
    0.50
    的方式
    0.49
     way
    0.48
    POSITIVE LOGITS
     얼마나
    2.42
     сколько
    2.20
     combien
    2.16
     कितना
    2.09
     cuánto
    2.06
     कितनी
    2.05
     किती
    2.05
     quanto
    2.03
     насколько
    1.99
     how
    1.98
    Act Density 0.100%

    No Known Activations