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

    Neuronpedia

    INDEX
    Explanations

    words containing bal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    নো
    0.43
    slug
    0.40
    Ale
    0.40
    Hudson
    0.40
     پایه
    0.40
    Rabbit
    0.38
    allis
    0.37
     спі
    0.37
    ليا
    0.36
    ظل
    0.36
    POSITIVE LOGITS
     bal
    0.83
     Bal
    0.77
     BAL
    0.77
    Bal
    0.73
     Бала
    0.71
     sheet
    0.67
     Balancing
    0.65
     Sheet
    0.65
    BAL
    0.64
     бала
    0.60
    Act Density 0.012%

    No Known Activations