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

    Neuronpedia

    INDEX
    Explanations

    existing items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мә
    0.45
    快樂
    0.45
     бясплат
    0.44
    풋
    0.43
     ordinances
    0.43
    くれます
    0.42
    梔
    0.42
    驪
    0.42
    緝
    0.41
    緘
    0.41
    POSITIVE LOGITS
    es
    0.46
    src
    0.45
    left
    0.43
    ids
    0.43
    ormous
    0.43
    files
    0.43
    arrays
    0.42
    bs
    0.42
    loaded
    0.42
     massively
    0.42
    Act Density 0.012%

    No Known Activations