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

    Neuronpedia

    INDEX
    Explanations

    Grade Level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্টের
    0.44
     Hö
    0.42
    '_{
    0.42
    ore
    0.40
    উন্ট
    0.40
    rott
    0.39
    IE
    0.38
     ইউনিভার্সি
    0.38
    äst
    0.38
    ология
    0.37
    POSITIVE LOGITS
     level
    0.91
     nível
    0.75
     nivel
    0.75
     niveau
    0.74
     levels
    0.72
    level
    0.72
     LEVEL
    0.69
     livello
    0.68
     niveaux
    0.67
     수준
    0.66
    Act Density 0.003%

    No Known Activations