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

    Neuronpedia

    INDEX
    Explanations

    compound interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    1.93
    peč
    1.61
    re
    1.58
    enregistrement
    1.53
    आती
    1.53
    𝑃
    1.49
    યો
    1.40
    ر
    1.39
    ্তিক
    1.38
    emptyset
    1.37
    POSITIVE LOGITS
     mínimo
    2.09
     gotta
    1.95
     Elk
    1.94
     bezier
    1.89
     mL
    1.84
    eller
    1.82
    んばんは
    1.81
     hn
    1.81
     Tsuk
    1.80
     inception
    1.79
    Act Density 0.000%

    No Known Activations