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

    Neuronpedia

    INDEX
    Explanations

    specific word followed by function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     period
    0.57
     période
    0.57
    period
    0.55
    时期
    0.51
     期
    0.50
    Period
    0.49
     период
    0.49
    期
    0.47
     periode
    0.47
     पीरियड
    0.46
    POSITIVE LOGITS
     intención
    0.46
     plă
    0.43
     compounds
    0.41
     প্ল
    0.39
     ഭ
    0.39
    כז
    0.39
    เก็บ
    0.39
    மொழ
    0.39
    між
    0.38
     contened
    0.38
    Act Density 0.000%

    No Known Activations