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

    Neuronpedia

    INDEX
    Explanations

    family and friends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ையுடன்
    0.33
     hadn
    0.30
     suits
    0.29
     connector
    0.28
     worked
    0.28
    Биография
    0.28
    ្នែក
    0.28
     callBack
    0.28
     elapsed
    0.28
    ："
    0.27
    POSITIVE LOGITS
    ,
    0.42
    ،
    0.32
     Canva
    0.29
     linguistique
    0.29
    ,.
    0.28
    ਲ
    0.28
    ,_
    0.28
     minimale
    0.28
     Mga
    0.27
    ,!
    0.27
    Act Density 0.043%

    No Known Activations