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

    Neuronpedia

    INDEX
    Explanations

    statistical power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Divers
    0.44
    со
    0.43
     निः
    0.41
     Sich
    0.39
     সুল
    0.39
    compan
    0.38
    лко
    0.38
     intermédiaire
    0.38
     caro
    0.38
     bek
    0.38
    POSITIVE LOGITS
     Steelers
    0.44
    ുകളിൽ
    0.42
     Fulham
    0.41
     Lakers
    0.40
     Kyrie
    0.40
    Houses
    0.39
     swatch
    0.38
     Ryzen
    0.37
     Manchester
    0.37
     ветра
    0.37
    Act Density 0.000%

    No Known Activations