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

    Neuronpedia

    INDEX
    Explanations

    concluding words and list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     інших
    0.44
    いたり
    0.40
    েই
    0.38
    妹
    0.38
    或其他
    0.37
    യു
    0.37
     ቡ
    0.35
     หาร
    0.34
    元年
    0.34
    ছিল
    0.34
    POSITIVE LOGITS
     અને
    0.44
     enfin
    0.42
     आणि
    0.42
     Finally
    0.41
     및
    0.41
    そして
    0.41
     lastly
    0.41
     және
    0.41
     finally
    0.40
     Lastly
    0.40
    Act Density 0.283%

    No Known Activations