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

    Neuronpedia

    INDEX
    Explanations

    numbers, currency, and royal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     H
    0.61
     L
    0.59
     to
    0.58
     N
    0.56
     n
    0.55
     C
    0.54
     R
    0.53
     O
    0.52
     p
    0.52
     d
    0.52
    POSITIVE LOGITS
     уйнау
    0.51
    <unused1063>
    0.51
    <unused447>
    0.49
    ર્સ
    0.49
     ఆదాయ
    0.49
    <unused210>
    0.48
     уены
    0.47
    riminating
    0.47
    <unused378>
    0.46
    гій
    0.46
    Act Density 0.000%

    No Known Activations