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

    Neuronpedia

    INDEX
    Explanations

    geo data, curve fit, virtual care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.40
    ).
    0.40
    ]{\
    0.37
    ̣
    0.37
     Jamestown
    0.35
    Philipp
    0.34
    ):
    0.33
     apolog
    0.33
     is
    0.33
     Behavioral
    0.33
    POSITIVE LOGITS
     ऐप्स
    0.48
     решения
    0.43
    у
    0.41
     앱
    0.40
     सॉल्यू
    0.40
     एस्ट्र
    0.40
     guru
    0.39
     bitcoins
    0.39
    大数据
    0.39
     cesse
    0.39
    Act Density 0.008%

    No Known Activations