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

    Neuronpedia

    INDEX
    Explanations

    speed and performance measures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    人們
    0.52
     Ashanti
    0.51
    ப்பிரிக்க
    0.50
     hernia
    0.49
     knn
    0.47
     winemaker
    0.47
     FHWA
    0.47
     bumpy
    0.47
     outs
    0.46
    흙
    0.46
    POSITIVE LOGITS
    ablo
    0.50
    وف
    0.50
    vede
    0.49
    +
    0.46
    ef
    0.46
     assegn
    0.44
    产生
    0.43
    erede
    0.42
    دا
    0.42
     alap
    0.40
    Act Density 0.000%

    No Known Activations