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

    Neuronpedia

    INDEX
    Explanations

    time and date formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    queryset
    0.55
    Serializer
    0.50
    qs
    0.44
     annealed
    0.44
    Slug
    0.42
     queryset
    0.42
     qubit
    0.41
    annotate
    0.41
     детям
    0.41
    serializer
    0.41
    POSITIVE LOGITS
     Lifestyle
    0.39
     chron
    0.38
    静
    0.38
     prêt
    0.38
    Lifestyle
    0.38
     micro
    0.37
     ferro
    0.36
    ścio
    0.36
     som
    0.35
     静
    0.35
    Act Density 0.083%

    No Known Activations