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

    Neuronpedia

    INDEX
    Explanations

    abstract qualities and virtues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     যেসব
    0.29
    τικές
    0.27
     treatments
    0.27
     formulations
    0.25
     implementations
    0.25
     प्रदू
    0.25
     traitements
    0.25
     ways
    0.24
    ंजनों
    0.24
     technologies
    0.24
    POSITIVE LOGITS
     versatility
    0.56
     ingenuity
    0.55
     sophistication
    0.55
     normalcy
    0.55
     authenticity
    0.54
     sincerity
    0.53
     brevity
    0.53
     athleticism
    0.53
     dynamism
    0.53
     humility
    0.52
    Act Density 0.425%

    No Known Activations