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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis followed by opening brace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jenigen
    2.22
     spéc
    2.03
    از
    1.90
    Если
    1.85
    ാപാ
    1.83
    Когда
    1.82
     stellt
    1.82
     professionnels
    1.80
    พลาด
    1.75
    від
    1.74
    POSITIVE LOGITS
    ية
    2.26
    та
    2.09
    го
    2.08
    س
    2.07
    tong
    2.03
    ন
    2.02
    जफ्
    1.91
    ী
    1.88
    {}
    1.87
    TER
    1.87
    Act Density 0.001%

    No Known Activations