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

    Neuronpedia

    INDEX
    Explanations

    same as / same way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ческих
    1.18
     Одна
    1.04
    specifically
    0.99
    मर्श
    0.97
     మాత్రమే
    0.97
    Qui
    0.94
     convirtió
    0.94
    triggered
    0.93
    Gly
    0.93
    ンド
    0.92
    POSITIVE LOGITS
     thing
    1.70
     amount
    1.48
     vein
    1.47
    സമയം
    1.34
     exact
    1.33
     zamanda
    1.32
    WeekDates
    1.29
     magnitude
    1.25
     ilk
    1.24
     şeyi
    1.22
    Act Density 0.057%

    No Known Activations