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

    Neuronpedia

    INDEX
    Explanations

    in short summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.94
    ,
    0.87
    、
    0.87
    (),
    0.77
    ，
    0.76
    ^+,
    0.73
    ፣
    0.70
     أيضا
    0.69
    ,(
    0.68
     ፣
    0.68
    POSITIVE LOGITS
    ۔۔
    0.76
    …"
    0.75
    :...
    0.75
    :.
    0.74
    ・・・
    0.71
    :""
    0.70
    …….
    0.70
    ..."
    0.69
    ...."
    0.68
    ↵↵
    0.68
    Act Density 0.033%

    No Known Activations