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

    Neuronpedia

    INDEX
    Explanations

    Q2 or quarter 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ის
    0.63
    monthly
    0.63
    schein
    0.61
    sure
    0.59
    ться
    0.59
    きっと
    0.58
    Monthly
    0.58
    ómica
    0.58
    spectra
    0.57
    <unused79>
    0.56
    POSITIVE LOGITS
    t
    0.71
     mesurer
    0.63
    ERSON
    0.62
     classify
    0.61
    ত
    0.59
     disparate
    0.55
     enum
    0.55
    㞱
    0.54
    ليم
    0.54
    :
    0.54
    Act Density 0.001%

    No Known Activations