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

    Neuronpedia

    INDEX
    Explanations

    compounding returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forfeiture
    0.49
     permittivity
    0.44
     percentages
    0.43
     pausing
    0.43
     tonal
    0.43
     monotonicity
    0.42
     professor
    0.42
     glitches
    0.42
     frequencies
    0.41
     faults
    0.41
    POSITIVE LOGITS
    얻
    0.44
     얻
    0.43
     یاد
    0.40
     ইউ
    0.40
     י
    0.39
    的一些
    0.38
     جي
    0.38
     воспомина
    0.38
     Heck
    0.38
     دي
    0.37
    Act Density 0.013%

    No Known Activations