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

    Neuronpedia

    INDEX
    Explanations

    pricing, targeting, scheduling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‌ی
    2.78
    ’
    2.61
    ‌ای
    2.34
     habido
    2.06
    ️
    1.88
    sst
    1.83
     filings
    1.80
    ى
    1.80
     teeming
    1.79
     happenings
    1.78
    POSITIVE LOGITS
    ع
    3.59
    他
    2.41
    redients
    2.25
    ส์
    2.23
     როგორც
    2.19
    𝘺
    2.19
    被
    2.17
    ش
    2.14
    一起
    2.08
    ly
    2.03
    Act Density 1.672%

    No Known Activations