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

    Neuronpedia

    INDEX
    Explanations

    cell, energy, organic, growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beginners
    0.45
     worksheets
    0.43
     commencent
    0.43
     lemmas
    0.43
    ោះស្រាយ
    0.42
    这样做
    0.42
     వాటి
    0.41
     pelajaran
    0.41
     nové
    0.41
     Caed
    0.41
    POSITIVE LOGITS
    :
    0.59
    Be
    0.44
     Natural
    0.41
     Cell
    0.39
     H
    0.38
     E
    0.38
     Couture
    0.38
     V
    0.38
     Social
    0.38
     Energy
    0.38
    Act Density 0.001%

    No Known Activations