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

    Neuronpedia

    INDEX
    Explanations

    SHOP, vaccine, purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     嗯
    0.51
     노래
    0.49
     시간
    0.48
     komme
    0.48
    ധിപ
    0.48
    疃
    0.47
     nghịch
    0.45
     시간을
    0.45
     aank
    0.44
     дыха
    0.44
    POSITIVE LOGITS
    #.
    0.43
    ﺗ
    0.43
    薊
    0.42
     W
    0.41
    യിലാണ്
    0.41
     shipbuilding
    0.40
    ↵
    0.40
     ladle
    0.40
    .
    0.40
    ם
    0.40
    Act Density 0.001%

    No Known Activations