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

    Neuronpedia

    INDEX
    Explanations

    deluge, delphi, testing, games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thawing
    0.47
    ônico
    0.44
     uncanny
    0.44
     Statutory
    0.43
    achen
    0.43
     হইয়াছিলেন
    0.42
     passivation
    0.42
    ellae
    0.42
     sarcom
    0.42
    onitrile
    0.41
    POSITIVE LOGITS
    을
    0.58
    Есть
    0.55
    Мар
    0.54
    ER
    0.53
     INIS
    0.53
    を入
    0.52
    Можно
    0.50
    ﾙ
    0.50
    Sean
    0.49
    Sono
    0.49
    Act Density 0.389%

    No Known Activations