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

    Neuronpedia

    INDEX
    Explanations

    potential outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᆼ
    0.80
    ра
    0.72
    รุ่น
    0.66
     bumpy
    0.63
    ፣
    0.63
    င်
    0.63
    ри
    0.62
    на
    0.61
     foreseeable
    0.61
     önemlidir
    0.61
    POSITIVE LOGITS
    5
    0.64
     Wszyst
    0.63
    י
    0.62
    いに
    0.62
    ﺎ
    0.62
    4
    0.60
    న్నారు
    0.60
    ARI
    0.60
    1
    0.60
    slot
    0.59
    Act Density 0.109%

    No Known Activations