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

    Neuronpedia

    INDEX
    Explanations

    recognizing patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deaktiv
    0.54
     pemilik
    0.45
    évaluation
    0.42
     ayrıca
    0.41
     شفاف
    0.41
     öffentliche
    0.41
     quería
    0.39
    عند
    0.39
     calificación
    0.38
     competit
    0.38
    POSITIVE LOGITS
     patterns
    1.28
     pattern
    1.13
     Patterns
    1.13
    Patterns
    1.12
    パターン
    1.10
    patterns
    1.06
     패턴
    1.03
    pattern
    1.02
    Pattern
    0.95
     पैटर्न
    0.95
    Act Density 0.197%

    No Known Activations