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

    Neuronpedia

    INDEX
    Explanations

    effective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    প
    0.43
    滿足
    0.41
     शर्तें
    0.40
     محصول
    0.40
     sikre
    0.40
    有时候
    0.39
     बोनस
    0.39
    შე
    0.39
     Innoc
    0.39
    人數
    0.38
    POSITIVE LOGITS
    href
    0.40
    rte
    0.38
     RID
    0.37
    fool
    0.36
     voci
    0.36
    reiber
    0.36
    迄
    0.35
    mixed
    0.35
    Distinct
    0.35
    шет
    0.34
    Act Density 0.002%

    No Known Activations