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

    Neuronpedia

    INDEX
    Explanations

    quite the opposite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dh
    0.49
    دان
    0.44
    URE
    0.43
    <h3>
    0.42
    <h4>
    0.42
    ipt
    0.41
    dbo
    0.41
    den
    0.41
    жать
    0.40
    ogue
    0.39
    POSITIVE LOGITS
     quite
    0.74
     frankly
    0.71
     abit
    0.68
     bastante
    0.64
     alot
    0.63
     literally
    0.58
    quite
    0.57
     हद
    0.55
     khá
    0.55
     astonishing
    0.53
    Act Density 0.004%

    No Known Activations