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

    Neuronpedia

    INDEX
    Explanations

    decalog about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Пар
    0.58
     Гуляць
    0.53
     relazione
    0.50
     दूसरों
    0.50
     Дру
    0.50
    荃
    0.50
     zamknię
    0.49
    ار
    0.49
     ګرځ
    0.49
    举
    0.49
    POSITIVE LOGITS
     renovate
    0.43
     applying
    0.42
    Swiss
    0.42
     amino
    0.41
     acoustics
    0.41
    ENS
    0.41
    HT
    0.40
    anke
    0.40
    推出了
    0.40
     hypertext
    0.40
    Act Density 0.000%

    No Known Activations