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

    Neuronpedia

    INDEX
    Explanations

    dates and ordinals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     je
    0.91
     puluh
    0.91
    ઓને
    0.84
     얼마나
    0.79
     Cos
    0.77
     Nota
    0.74
    ging
    0.73
     отдельные
    0.73
    tenths
    0.73
     restoran
    0.72
    POSITIVE LOGITS
    st
    1.14
     забезпечення
    0.86
    ؎
    0.85
    setAttribute
    0.84
    facilities
    0.81
     inconsistencies
    0.81
    stArray
    0.80
     Initiatives
    0.80
     liners
    0.79
    ⃙
    0.79
    Act Density 0.025%

    No Known Activations