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

    Neuronpedia

    INDEX
    Explanations

    why it's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ませんでした
    0.47
     does
    0.46
     did
    0.46
    はありません
    0.44
    did
    0.43
     DOES
    0.43
     DID
    0.43
    does
    0.42
    となりました
    0.42
    はなく
    0.42
    POSITIVE LOGITS
     theyre
    1.00
     youre
    0.95
     estás
    0.71
     estamos
    0.69
     thats
    0.65
     theres
    0.65
     इट्स
    0.64
     εί
    0.64
     whats
    0.64
     siamo
    0.63
    Act Density 0.068%

    No Known Activations