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

    Neuronpedia

    INDEX
    Explanations

    differences and changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hipster
    0.45
     arrogant
    0.41
     kullanılır
    0.40
     hùng
    0.39
     Geschäft
    0.38
    屌
    0.38
     চালায়
    0.38
    管控
    0.37
    男人
    0.37
     horrend
    0.37
    POSITIVE LOGITS
     discrepancies
    0.56
     differences
    0.53
     changes
    0.52
     that
    0.50
     variations
    0.49
     disparities
    0.46
     variation
    0.45
     improvements
    0.44
    的這個
    0.44
     modifications
    0.42
    Act Density 0.002%

    No Known Activations