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

    Neuronpedia

    INDEX
    Explanations

    problematic states or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pricing
    0.50
     সুবিধ
    0.48
    融资
    0.47
     pricing
    0.46
    的价格
    0.45
     간단
    0.45
     Marketing
    0.44
     가격
    0.43
     để
    0.42
     stratég
    0.41
    POSITIVE LOGITS
     excessively
    0.71
     improperly
    0.70
     exposures
    0.66
     trauma
    0.65
     insufficiently
    0.65
     prolonged
    0.62
     excessive
    0.61
     abnormally
    0.58
     exposure
    0.58
     overuse
    0.58
    Act Density 0.152%

    No Known Activations