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

    Neuronpedia

    INDEX
    Explanations

    Gaussian blur, kernel size, sigma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     команд
    0.57
    崆
    0.52
    =".
    0.47
    ंपूर्
    0.47
     utilize
    0.47
     интервью
    0.46
    чук
    0.46
     ።
    0.46
     calorimetric
    0.46
     रेशियो
    0.46
    POSITIVE LOGITS
     terem
    0.45
     B
    0.44
     banyaknya
    0.44
     fez
    0.43
     wal
    0.43
     morgen
    0.42
    ley
    0.42
     I
    0.42
     fast
    0.41
     foi
    0.41
    Act Density 0.001%

    No Known Activations