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

    Neuronpedia

    INDEX
    Explanations

    Therefore following so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ない
    0.31
     která
    0.28
    0.28
     undone
    0.27
     그래도
    0.27
     otherwise
    0.27
     kuiten
    0.27
    しまった
    0.26
     solchen
    0.26
     sare
    0.26
    POSITIVE LOGITS
    ،
    0.43
    യാണ്
    0.41
    ፣
    0.40
    ၊
    0.37
    .$,
    0.35
    ,
    0.35
    ‌,
    0.34
    ，
    0.34
    $,
    0.32
    ,$$
    0.32
    Act Density 0.049%

    No Known Activations